K

kibi

looted/kibi · v0.0.0 · Tools & Integrations

by LootedOwner verifiedScan grade: GoodAwesome AI Plugins

MCP server and per-agent plugins that compile product intent into structured requirements and check that code and tests stay consistent with them

Follow0
Protect this install with HOL Guard

Guard checks the skills and MCP servers a plugin adds on your machine and asks you before a risky action runs. The scores above are free, and no plan changes them.

Is kibi a fit?

From the plugin's manifest and HOL's scan. Anything the plugin does not declare is shown as not declared.

Works with

  • Standalone
  • 61 skills
  • 1 MCP server

Before you install

Sign-in
Not declared
Declared access
Not declared
License
Not declared

Check before relying on it

  • Some security checks did not finish: Cisco skill scan and Cisco MCP scan. See the evidence
  • 5 medium findings from the scan. See the evidence
  • No license declared in the manifest.

What is kibi?

kibi is a published tools & integrations plugin for AI coding agents in the Standalone ecosystem, developed by Looted and distributed through the HOL AI plugin registry. MCP server and per-agent plugins that compile product intent into structured requirements and check that code and tests stay consistent with them.

Canonical slug
looted/kibi
Version
v0.0.0 · updated Nov 19, 2026

Registry snapshot

Owner verification
Verified on HOL as @Looted
Marketplace source
.claude-plugin/marketplace.json
Scanner
HOL plugin scanner
Security result
Needs review
Digest verified
Yes
61 bundled skillsRead, copy or download each SKILL.mdOpen skills

Trust and security

Trust & reputation

On-Chain Verified
77

HOL Trust Score

Per-metric points (0–100 each) combined via a weighted average into the overall score.

Installability
71/100
Maintenance
90/100
MCP server setup
100/100
Plugin Security
85/100
Provenance
80/100
Publisher Quality
100/100

Provenance

Plugin root
.
Source repo
https://github.com/Looted/kibi
Source commit
151293bb6e50…
Publisher verified
Yes
Owner verified
@Looted
Agent Plugins 1.0
Not detected

Continuous scanner CI not detected

This plugin remains listed. Its overall trust score is reduced by 10% because security checks are not maintained in the source repository's CI.

Optional: maintain the scanner in the source repository's CI to receive the full trust score. Listing does not require that change.

README badge not detected

Plugin owners can add the HOL badge to the repository README from Guard Plugins. Distribution, not security evidence. It adds a 2% engagement adjustment to the overall trust score and never changes the security result.

Needs review
Security result
85
Security score
0
High findings
Provider
codex-plugin-scanner
Grade
B · Good
Version
3.24.2
codex:hol-plugin-scanner-21qqvt / cisco-skill-scanner: failedcodex:hol-plugin-scanner-21qqvt / cisco-mcp-scanner: unavailable

[claude:.] Claude Plugin

22/22

5 checks

[claude:.] Security

20/20

6 checks

[claude:.] Operational Security

3/6

5 checks

[claude:.] Code Quality

10/10

2 checks

[codex:.] Manifest Validation

13/31

9 checks

[codex:.] Security

20/20

9 checks

[codex:.] Operational Security

3/6

5 checks

[codex:.] Best Practices

9/12

5 checks

[codex:.] Marketplace

15/15

3 checks

[codex:.] Skill Security

5/5

4 checks

[codex:.] Code Quality

10/10

2 checks

[opencode:.] OpenCode Plugin

5/5

4 checks

[opencode:.] Security

20/20

6 checks

[opencode:.] Operational Security

3/6

5 checks

[opencode:.] Code Quality

10/10

2 checks

Published advisories

None matched in GitHub security advisories, checked . This covers published advisories only, not problems nobody has reported.

GitHub security advisories are those the source repository has published.

Findings

mediumoperational-securityDEPENDENCY_LOCKFILE_MISSINGReported 3 times

package.json is present without a corresponding lockfile or pinned dependency snapshot.

Commit a lockfile or use fully pinned requirements for reproducible dependency resolution.

mediummanifest-validationPLUGIN_JSON_MISSING_VERSION

The manifest does not define a valid string for "version".

Add a non-empty string value for "version" in plugin.json.

mediummanifest-validationPLUGIN_JSON_MISSING_DESCRIPTION

The manifest does not define a valid string for "description".

Add a non-empty string value for "description" in plugin.json.

lowmanifest-validationPLUGIN_JSON_BAD_SEMVER

The version "" does not match the documented semver format.

Use a version like 1.2.3 in plugin.json.

infomanifest-validationPLUGIN_JSON_RECOMMENDED_AUTHOR

The manifest is missing the documented recommended field "author".

Add "author" to strengthen the plugin manifest metadata.

infomanifest-validationPLUGIN_JSON_RECOMMENDED_HOMEPAGE

The manifest is missing the documented recommended field "homepage".

Add "homepage" to strengthen the plugin manifest metadata.

infomanifest-validationPLUGIN_JSON_RECOMMENDED_LICENSE

The manifest is missing the documented recommended field "license".

Add "license" to strengthen the plugin manifest metadata.

infomanifest-validationPLUGIN_JSON_RECOMMENDED_KEYWORDS

The manifest is missing the documented recommended field "keywords".

Add "keywords" to strengthen the plugin manifest metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_SHORTDESCRIPTION

The interface object is missing a valid "shortDescription" value.

Add a valid "shortDescription" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_LONGDESCRIPTION

The interface object is missing a valid "longDescription" value.

Add a valid "longDescription" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_CATEGORY

The interface object is missing a valid "category" value.

Add a valid "category" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_CAPABILITIES

The interface object is missing a valid "capabilities" value.

Add a valid "capabilities" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_WEBSITEURL

The interface field "websiteURL" must use HTTPS or point to a safe in-repo asset.

Update "websiteURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_PRIVACYPOLICYURL

The interface field "privacyPolicyURL" must use HTTPS or point to a safe in-repo asset.

Update "privacyPolicyURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_TERMSOFSERVICEURL

The interface field "termsOfServiceURL" must use HTTPS or point to a safe in-repo asset.

Update "termsOfServiceURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_COMPOSERICON

The interface field "composerIcon" must use HTTPS or point to a safe in-repo asset.

Update "composerIcon" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_LOGO

The interface field "logo" must use HTTPS or point to a safe in-repo asset.

Update "logo" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_SCREENSHOTS

The interface field "screenshots" must use HTTPS or point to a safe in-repo asset.

Update "screenshots" to use HTTPS or an existing relative asset path.

infobest-practicesCODEXIGNORE_MISSING

A .codexignore file helps prevent accidental inclusion of local artifacts and secrets.

Add a .codexignore file with generated assets, local state, and secret paths.

Install guidance

Install in Source

Install from a native release archive or the assessed source revision.

Install guide
  1. 1

    Download the release archive

    Use a published GitHub release archive. The catalog version is the package version at the assessed commit.

    shell
  2. 2

    Follow the publisher install guide

    https://github.com/Looted/kibi/blob/151293bb6e50ff3324d32513b5913a4a3080dc21/docs/INSTALL.md

Did setup work in Source?

No setup reports for Source yet. Self-reported by signed-in visitors. Copying a command is not counted, and most installs are never reported.

Attested installs: Fewer than 10 attested installs of this plugin in week 2026-W46, so no number is shown. Counted from opt-in HOL Guard install reports, once per machine and runtime, and never mixed with the answers above. How install reports work.

Loading reviews

Plugin manifest

{
  "name": "kibi",
  "displayName": "Kibi",
  "owner": {
    "name": "Kibi"
  },
  "metadata": {
    "description": "Repo-scoped Cursor plugins for Kibi workflows",
    "pluginRoot": "plugins"
  },
  "plugins": [
    {
      "name": "kibi-cursor",
      "source": "kibi-cursor",
      "description": "Optional Cursor adapter for Kibi. Prerequisite: project-local kibi-cli, kibi-mcp, kibi-core; SWI-Prolog is bundled on Linux and macOS (see docs/install.md). Bundles MCP config, rules, skills, commands, and advisory hooks.",
      "homepage": "https://github.com/Looted/kibi/blob/develop/docs/install.md",
      "repository": "https://github.com/Looted/kibi",
      "keywords": [
        "kibi",
        "mcp",
        "knowledge-base",
        "traceability",
        "swi-prolog"
      ],
      "tags": [
        "prerequisites",
        "mcp",
        "cli"
      ]
    },
    {
      "name": "kibi-agent-plugin",
      "source": "kibi-agent-plugin",
      "description": "Portable Agent Plugins build of Kibi (agent-plugins.org). Packages Kibi's Agent Skills and MCP server for any client that supports the open standard. Prerequisite: project-local kibi-cli, kibi-mcp, kibi-core; SWI-Prolog is bundled on Linux and macOS (see docs/install.md).",
      "homepage": "https://github.com/Looted/kibi/blob/develop/docs/install.md",
      "repository": "https://github.com/Looted/kibi",
      "keywords": [
        "kibi",
        "mcp",
        "knowledge-base",
        "traceability",
        "agent-plugins",
        "swi-prolog"
      ],
      "tags": [
        "prerequisites",
        "mcp",
        "cli",
        "portable"
      ]
    }
  ],
  "repository": "https://github.com/Looted/kibi",
  "interface": {
    "displayName": "Kibi",
    "developerName": "Looted"
  },
  "skills": "./",
  "mcpServers": "./.registry/mcp.json",
  "holManifestOrigin": "repository",
  "registryIndexVersion": 9
}

Marketplace source

Repo URL
https://github.com/Looted/kibi
Marketplace path
.claude-plugin/marketplace.json
Source path
.
Install policy
Unspecified

Skills

61 SKILL.md files ship with this plugin. Preview, copy, or download each one, then install them with the Skills CLI.

Share
skills-cli
  • kibi-freshness

    documentation/evaluations/skillopt/proposals/2026-10-04/kibi-freshness/SKILL.md

    Check exact Git attachment, branch migration/quarantine, compiled-store freshness, source linkage, and repair state before decisions or writes.

    Raw SKILL.md
  • kibi-freshness

    documentation/evaluations/skillopt/proposals/2026-10-20/kibi-freshness/SKILL.md

    Check exact Git attachment, branch migration/quarantine, compiled-store freshness, source linkage, and repair state before decisions or writes.

    Raw SKILL.md
  • kibi-traceability

    documentation/evaluations/skillopt/proposals/2026-10-20/kibi-traceability/SKILL.md

    Maintain source-first requirement, scenario, test, symbol, and proof traceability through Kibi's peer interfaces.

    Raw SKILL.md
  • Kibi Usage

    documentation/evaluations/skillopt/proposals/2026-10-20/kibi-usage/SKILL.md

    Use Kibi's source-first, exact-Git, migration-aware, proof-aware operations safely across MCP or the trusted local CLI, including partial completion repair.

    Raw SKILL.md
  • kibi-freshness

    documentation/evaluations/skillopt/proposals/2026-10-21/kibi-freshness/SKILL.md

    Check exact Git attachment, branch migration/quarantine, compiled-store freshness, source linkage, and repair state before decisions or writes.

    Raw SKILL.md
  • kibi-traceability

    documentation/evaluations/skillopt/proposals/2026-10-21/kibi-traceability/SKILL.md

    Maintain source-first requirement, scenario, test, symbol, and proof traceability through Kibi's peer interfaces.

    Raw SKILL.md
  • kibi-traceability

    documentation/evaluations/skillopt/proposals/2026-10-21b/kibi-traceability/SKILL.md

    Maintain source-first requirement, scenario, test, symbol, and proof traceability through Kibi's peer interfaces.

    Raw SKILL.md
  • Kibi Usage

    documentation/evaluations/skillopt/proposals/2026-10-22/kibi-usage/SKILL.md

    Use Kibi's source-first, exact-Git, migration-aware, proof-aware operations safely across MCP or the trusted local CLI, including partial completion repair.

    Raw SKILL.md
  • kibi-commit-review

    documentation/evaluations/skillopt/proposals/2026-10-22b/kibi-commit-review/SKILL.md

    Use when kibi check --staged or the Kibi pre-commit hook blocks a commit (kibi_impact_evidence_missing, symbols_manifest_stale, symbol_granularity_violation, symbol-coverage, kibi check-generated drift, Staged impact review failed), or when preparing a commit or pull-request impact review. Covers reading the per-file Detail lines, authoring .kb/symbols.yaml symbol entries through kb_upsert, kibi sync --refresh-symbol-coordinates, staging the tracked Kibi evidence with git add, kb_prepare_impact_review for a staged or diff scope, and how merge commits and migration renames are judged.

    Raw SKILL.md
  • kibi-decisions

    documentation/evaluations/skillopt/proposals/2026-10-22c/kibi-decisions/SKILL.md

    Use when the person states a rule or decision (must, never, always, from now on, we decided), when a Kibi hook asks to confirm or warns about an edit to code that implements a firm requirement, when the Stop hook says source files changed but nothing was recorded, when kb_check quotes requirement_statement_unverified, or when a request conflicts with a recorded requirement or ADR. Covers reading firmness and origin, recording a person's rule as firm with origin.ref, superseding with a Why this changed section, the kb_compile_intent unresolved/reviewCandidates/conflictReviews loop, asking before overriding a firm rule, and putting decisions to the person as one numbered kibi signoff --questions view.

    Raw SKILL.md
  • Kibi Usage

    documentation/evaluations/skillopt/proposals/2026-10-22d/kibi-usage/SKILL.md

    Use Kibi's source-first, exact-Git, migration-aware, proof-aware operations safely across MCP or the trusted local CLI, including partial completion repair.

    Raw SKILL.md
  • kibi-bootstrap

    packages/claude/skills/kibi-bootstrap/SKILL.md

    Use for any Kibi bootstrap or onboarding task: seeding a new or thin knowledge base; reviewing a bootstrap or onboarding plan, preview, or evidence; judging approval readiness or coverage; diagnosing a blocked, partial, or failed bootstrap or its repair; applying an approved bootstrap plan; or asking the human which knowledge sources hold intent. Covers kb_status first, source interview, cited intent claims, read-only kb_plan_bootstrap preview, explicit approval, exact-plan kb_apply_plan, and repair-safe close-out.

    Raw SKILL.md
  • kibi-commit-review

    packages/claude/skills/kibi-commit-review/SKILL.md

    Use when kibi check --staged or the Kibi pre-commit hook blocks a commit (kibi_impact_evidence_missing, symbols_manifest_stale, symbol_granularity_violation, symbol-coverage, kibi check-generated drift, Staged impact review failed), or when preparing a commit or pull-request impact review. Covers reading the per-file Detail lines, authoring .kb/symbols.yaml symbol entries through kb_upsert, staging the tracked Kibi evidence with git add (symbol coordinates are derived and never staged), kb_prepare_impact_review for a staged or diff scope, the kibi signoff requirements summary to show before a commit, how merge commits and migration renames are judged, and which requirement a newly listed symbol belongs to without making that requirement too broad.

    Raw SKILL.md
  • kibi-decisions

    packages/claude/skills/kibi-decisions/SKILL.md

    Use when the person states a rule or decision (must, never, always, from now on, we decided), when a Kibi hook asks to confirm or warns about an edit to code that implements a firm requirement, when the Stop hook says source files changed but nothing was recorded, when kb_check quotes requirement_statement_unverified, or when a request conflicts with a recorded requirement or ADR. Covers reading firmness and origin, recording a person's rule as firm with origin.ref, superseding with a Why this changed section, the kb_compile_intent unresolved/reviewCandidates/conflictReviews loop, asking before overriding a firm rule, putting decisions to the person as one numbered kibi signoff --questions view, and getting a batch of statement changes, splits, reasons or retirements approved during a knowledge base cleanup.

    Raw SKILL.md
  • kibi-freshness

    packages/claude/skills/kibi-freshness/SKILL.md

    Check exact Git attachment, branch migration/quarantine, compiled-store freshness, source linkage, and repair state before decisions or writes.

    Raw SKILL.md
  • kibi-provable-code

    packages/claude/skills/kibi-provable-code/SKILL.md

    Use when writing, designing or refactoring code that implements a Kibi requirement (policies, limits, allow-lists, roles, state machines, routes, env and config reads, validators, error types), when a source proof or a value/domain read is refused because Kibi cannot read a name statically (a computed key, a dynamic import or require, eval, reflection, globals()[name], getattr with a computed name, $$var, a macro), or when deciding how to treat generated or vendored code. Covers design practices that make code easier to review, test and replace and that also let Kibi prove claims exactly, the line between a good refactor and a contortion for the tool, the accepted dynamic exceptions (plugins, serialization, registries), and generated code as a boundary.

    Raw SKILL.md
  • kibi-traceability

    packages/claude/skills/kibi-traceability/SKILL.md

    Maintain source-first requirement, scenario, test, symbol, and proof traceability through Kibi's peer interfaces. Use when linking a code symbol to a requirement (implements, covered_by, executable_for), choosing which function owns a behavior, moving or removing links, or when kb_check reports broad_requirement_review, multi_requirement_symbol_review, coarse_anchor_only_review, symbol-coverage or missing_production_symbol_coverage.

    Raw SKILL.md
  • kibi-usage

    packages/claude/skills/kibi-usage/SKILL.md

    Use Kibi's source-first, exact-Git, migration-aware, proof-aware operations safely across MCP or the trusted local CLI, including partial completion repair. Also use for knowledge base quality work: cleaning up or auditing a KB, clearing kibi check review findings (broad_requirement_review, multi_requirement_symbol_review, coarse_anchor_only_review, entity-context-missing), splitting a requirement that covers several behaviors, choosing which function owns a behavior, writing why a requirement exists, and retiring knowledge whose behavior is gone.

    Raw SKILL.md
  • kibi-bootstrap

    packages/cli/src/public/skills/kibi-bootstrap/SKILL.md

    Use for any Kibi bootstrap or onboarding task: seeding a new or thin knowledge base; reviewing a bootstrap or onboarding plan, preview, or evidence; judging approval readiness or coverage; diagnosing a blocked, partial, or failed bootstrap or its repair; applying an approved bootstrap plan; or asking the human which knowledge sources hold intent. Covers kb_status first, source interview, cited intent claims, read-only kb_plan_bootstrap preview, explicit approval, exact-plan kb_apply_plan, and repair-safe close-out.

    Raw SKILL.md
  • kibi-commit-review

    packages/cli/src/public/skills/kibi-commit-review/SKILL.md

    Use when kibi check --staged or the Kibi pre-commit hook blocks a commit (kibi_impact_evidence_missing, symbols_manifest_stale, symbol_granularity_violation, symbol-coverage, kibi check-generated drift, Staged impact review failed), or when preparing a commit or pull-request impact review. Covers reading the per-file Detail lines, authoring .kb/symbols.yaml symbol entries through kb_upsert, staging the tracked Kibi evidence with git add (symbol coordinates are derived and never staged), kb_prepare_impact_review for a staged or diff scope, the kibi signoff requirements summary to show before a commit, how merge commits and migration renames are judged, and which requirement a newly listed symbol belongs to without making that requirement too broad.

    Raw SKILL.md
  • kibi-decisions

    packages/cli/src/public/skills/kibi-decisions/SKILL.md

    Use when the person states a rule or decision (must, never, always, from now on, we decided), when a Kibi hook asks to confirm or warns about an edit to code that implements a firm requirement, when the Stop hook says source files changed but nothing was recorded, when kb_check quotes requirement_statement_unverified, or when a request conflicts with a recorded requirement or ADR. Covers reading firmness and origin, recording a person's rule as firm with origin.ref, superseding with a Why this changed section, the kb_compile_intent unresolved/reviewCandidates/conflictReviews loop, asking before overriding a firm rule, putting decisions to the person as one numbered kibi signoff --questions view, and getting a batch of statement changes, splits, reasons or retirements approved during a knowledge base cleanup.

    Raw SKILL.md
  • kibi-freshness

    packages/cli/src/public/skills/kibi-freshness/SKILL.md

    Check exact Git attachment, branch migration/quarantine, compiled-store freshness, source linkage, and repair state before decisions or writes.

    Raw SKILL.md
  • kibi-provable-code

    packages/cli/src/public/skills/kibi-provable-code/SKILL.md

    Use when writing, designing or refactoring code that implements a Kibi requirement (policies, limits, allow-lists, roles, state machines, routes, env and config reads, validators, error types), when a source proof or a value/domain read is refused because Kibi cannot read a name statically (a computed key, a dynamic import or require, eval, reflection, globals()[name], getattr with a computed name, $$var, a macro), or when deciding how to treat generated or vendored code. Covers design practices that make code easier to review, test and replace and that also let Kibi prove claims exactly, the line between a good refactor and a contortion for the tool, the accepted dynamic exceptions (plugins, serialization, registries), and generated code as a boundary.

    Raw SKILL.md
  • kibi-traceability

    packages/cli/src/public/skills/kibi-traceability/SKILL.md

    Maintain source-first requirement, scenario, test, symbol, and proof traceability through Kibi's peer interfaces. Use when linking a code symbol to a requirement (implements, covered_by, executable_for), choosing which function owns a behavior, moving or removing links, or when kb_check reports broad_requirement_review, multi_requirement_symbol_review, coarse_anchor_only_review, symbol-coverage or missing_production_symbol_coverage.

    Raw SKILL.md
  • Kibi Usage

    packages/cli/src/public/skills/kibi-usage/SKILL.md

    Use Kibi's source-first, exact-Git, migration-aware, proof-aware operations safely across MCP or the trusted local CLI, including partial completion repair. Also use for knowledge base quality work: cleaning up or auditing a KB, clearing kibi check review findings (broad_requirement_review, multi_requirement_symbol_review, coarse_anchor_only_review, entity-context-missing), splitting a requirement that covers several behaviors, choosing which function owns a behavior, writing why a requirement exists, and retiring knowledge whose behavior is gone.

    Raw SKILL.md
  • kibi-bootstrap

    packages/codex/skills/kibi-bootstrap/SKILL.md

    Use for any Kibi bootstrap or onboarding task: seeding a new or thin knowledge base; reviewing a bootstrap or onboarding plan, preview, or evidence; judging approval readiness or coverage; diagnosing a blocked, partial, or failed bootstrap or its repair; applying an approved bootstrap plan; or asking the human which knowledge sources hold intent. Covers kb_status first, source interview, cited intent claims, read-only kb_plan_bootstrap preview, explicit approval, exact-plan kb_apply_plan, and repair-safe close-out.

    Raw SKILL.md
  • kibi-commit-review

    packages/codex/skills/kibi-commit-review/SKILL.md

    Use when kibi check --staged or the Kibi pre-commit hook blocks a commit (kibi_impact_evidence_missing, symbols_manifest_stale, symbol_granularity_violation, symbol-coverage, kibi check-generated drift, Staged impact review failed), or when preparing a commit or pull-request impact review. Covers reading the per-file Detail lines, authoring .kb/symbols.yaml symbol entries through kb_upsert, staging the tracked Kibi evidence with git add (symbol coordinates are derived and never staged), kb_prepare_impact_review for a staged or diff scope, the kibi signoff requirements summary to show before a commit, how merge commits and migration renames are judged, and which requirement a newly listed symbol belongs to without making that requirement too broad.

    Raw SKILL.md
  • kibi-decisions

    packages/codex/skills/kibi-decisions/SKILL.md

    Use when the person states a rule or decision (must, never, always, from now on, we decided), when a Kibi hook asks to confirm or warns about an edit to code that implements a firm requirement, when the Stop hook says source files changed but nothing was recorded, when kb_check quotes requirement_statement_unverified, or when a request conflicts with a recorded requirement or ADR. Covers reading firmness and origin, recording a person's rule as firm with origin.ref, superseding with a Why this changed section, the kb_compile_intent unresolved/reviewCandidates/conflictReviews loop, asking before overriding a firm rule, putting decisions to the person as one numbered kibi signoff --questions view, and getting a batch of statement changes, splits, reasons or retirements approved during a knowledge base cleanup.

    Raw SKILL.md
  • kibi-freshness

    packages/codex/skills/kibi-freshness/SKILL.md

    Check exact Git attachment, branch migration/quarantine, compiled-store freshness, source linkage, and repair state before decisions or writes.

    Raw SKILL.md
  • kibi-provable-code

    packages/codex/skills/kibi-provable-code/SKILL.md

    Use when writing, designing or refactoring code that implements a Kibi requirement (policies, limits, allow-lists, roles, state machines, routes, env and config reads, validators, error types), when a source proof or a value/domain read is refused because Kibi cannot read a name statically (a computed key, a dynamic import or require, eval, reflection, globals()[name], getattr with a computed name, $$var, a macro), or when deciding how to treat generated or vendored code. Covers design practices that make code easier to review, test and replace and that also let Kibi prove claims exactly, the line between a good refactor and a contortion for the tool, the accepted dynamic exceptions (plugins, serialization, registries), and generated code as a boundary.

    Raw SKILL.md
  • kibi-traceability

    packages/codex/skills/kibi-traceability/SKILL.md

    Maintain source-first requirement, scenario, test, symbol, and proof traceability through Kibi's peer interfaces. Use when linking a code symbol to a requirement (implements, covered_by, executable_for), choosing which function owns a behavior, moving or removing links, or when kb_check reports broad_requirement_review, multi_requirement_symbol_review, coarse_anchor_only_review, symbol-coverage or missing_production_symbol_coverage.

    Raw SKILL.md
  • Kibi Usage

    packages/codex/skills/kibi-usage/SKILL.md

    Use Kibi's source-first, exact-Git, migration-aware, proof-aware operations safely across MCP or the trusted local CLI, including partial completion repair. Also use for knowledge base quality work: cleaning up or auditing a KB, clearing kibi check review findings (broad_requirement_review, multi_requirement_symbol_review, coarse_anchor_only_review, entity-context-missing), splitting a requirement that covers several behaviors, choosing which function owns a behavior, writing why a requirement exists, and retiring knowledge whose behavior is gone.

    Raw SKILL.md
  • kibi-bootstrap

    packages/cursor/agent-plugin/skills/kibi-bootstrap/SKILL.md

    Use for any Kibi bootstrap or onboarding task: seeding a new or thin knowledge base; reviewing a bootstrap or onboarding plan, preview, or evidence; judging approval readiness or coverage; diagnosing a blocked, partial, or failed bootstrap or its repair; applying an approved bootstrap plan; or asking the human which knowledge sources hold intent. Covers kb_status first, source interview, cited intent claims, read-only kb_plan_bootstrap preview, explicit approval, exact-plan kb_apply_plan, and repair-safe close-out.

    Raw SKILL.md
  • kibi-commit-review

    packages/cursor/agent-plugin/skills/kibi-commit-review/SKILL.md

    Use when kibi check --staged or the Kibi pre-commit hook blocks a commit (kibi_impact_evidence_missing, symbols_manifest_stale, symbol_granularity_violation, symbol-coverage, kibi check-generated drift, Staged impact review failed), or when preparing a commit or pull-request impact review. Covers reading the per-file Detail lines, authoring .kb/symbols.yaml symbol entries through kb_upsert, staging the tracked Kibi evidence with git add (symbol coordinates are derived and never staged), kb_prepare_impact_review for a staged or diff scope, the kibi signoff requirements summary to show before a commit, how merge commits and migration renames are judged, and which requirement a newly listed symbol belongs to without making that requirement too broad.

    Raw SKILL.md
  • kibi-decisions

    packages/cursor/agent-plugin/skills/kibi-decisions/SKILL.md

    Use when the person states a rule or decision (must, never, always, from now on, we decided), when a Kibi hook asks to confirm or warns about an edit to code that implements a firm requirement, when the Stop hook says source files changed but nothing was recorded, when kb_check quotes requirement_statement_unverified, or when a request conflicts with a recorded requirement or ADR. Covers reading firmness and origin, recording a person's rule as firm with origin.ref, superseding with a Why this changed section, the kb_compile_intent unresolved/reviewCandidates/conflictReviews loop, asking before overriding a firm rule, putting decisions to the person as one numbered kibi signoff --questions view, and getting a batch of statement changes, splits, reasons or retirements approved during a knowledge base cleanup.

    Raw SKILL.md
  • kibi-freshness

    packages/cursor/agent-plugin/skills/kibi-freshness/SKILL.md

    Check exact Git attachment, branch migration/quarantine, compiled-store freshness, source linkage, and repair state before decisions or writes.

    Raw SKILL.md
  • kibi-provable-code

    packages/cursor/agent-plugin/skills/kibi-provable-code/SKILL.md

    Use when writing, designing or refactoring code that implements a Kibi requirement (policies, limits, allow-lists, roles, state machines, routes, env and config reads, validators, error types), when a source proof or a value/domain read is refused because Kibi cannot read a name statically (a computed key, a dynamic import or require, eval, reflection, globals()[name], getattr with a computed name, $$var, a macro), or when deciding how to treat generated or vendored code. Covers design practices that make code easier to review, test and replace and that also let Kibi prove claims exactly, the line between a good refactor and a contortion for the tool, the accepted dynamic exceptions (plugins, serialization, registries), and generated code as a boundary.

    Raw SKILL.md
  • kibi-traceability

    packages/cursor/agent-plugin/skills/kibi-traceability/SKILL.md

    Maintain source-first requirement, scenario, test, symbol, and proof traceability through Kibi's peer interfaces. Use when linking a code symbol to a requirement (implements, covered_by, executable_for), choosing which function owns a behavior, moving or removing links, or when kb_check reports broad_requirement_review, multi_requirement_symbol_review, coarse_anchor_only_review, symbol-coverage or missing_production_symbol_coverage.

    Raw SKILL.md
  • Kibi Usage

    packages/cursor/agent-plugin/skills/kibi-usage/SKILL.md

    Use Kibi's source-first, exact-Git, migration-aware, proof-aware operations safely across MCP or the trusted local CLI, including partial completion repair. Also use for knowledge base quality work: cleaning up or auditing a KB, clearing kibi check review findings (broad_requirement_review, multi_requirement_symbol_review, coarse_anchor_only_review, entity-context-missing), splitting a requirement that covers several behaviors, choosing which function owns a behavior, writing why a requirement exists, and retiring knowledge whose behavior is gone.

    Raw SKILL.md
  • kibi-bootstrap

    packages/cursor/skills/kibi-bootstrap/SKILL.md

    Use for any Kibi bootstrap or onboarding task: seeding a new or thin knowledge base; reviewing a bootstrap or onboarding plan, preview, or evidence; judging approval readiness or coverage; diagnosing a blocked, partial, or failed bootstrap or its repair; applying an approved bootstrap plan; or asking the human which knowledge sources hold intent. Covers kb_status first, source interview, cited intent claims, read-only kb_plan_bootstrap preview, explicit approval, exact-plan kb_apply_plan, and repair-safe close-out.

    Raw SKILL.md
  • kibi-commit-review

    packages/cursor/skills/kibi-commit-review/SKILL.md

    Use when kibi check --staged or the Kibi pre-commit hook blocks a commit (kibi_impact_evidence_missing, symbols_manifest_stale, symbol_granularity_violation, symbol-coverage, kibi check-generated drift, Staged impact review failed), or when preparing a commit or pull-request impact review. Covers reading the per-file Detail lines, authoring .kb/symbols.yaml symbol entries through kb_upsert, staging the tracked Kibi evidence with git add (symbol coordinates are derived and never staged), kb_prepare_impact_review for a staged or diff scope, the kibi signoff requirements summary to show before a commit, how merge commits and migration renames are judged, and which requirement a newly listed symbol belongs to without making that requirement too broad.

    Raw SKILL.md
  • kibi-decisions

    packages/cursor/skills/kibi-decisions/SKILL.md

    Use when the person states a rule or decision (must, never, always, from now on, we decided), when a Kibi hook asks to confirm or warns about an edit to code that implements a firm requirement, when the Stop hook says source files changed but nothing was recorded, when kb_check quotes requirement_statement_unverified, or when a request conflicts with a recorded requirement or ADR. Covers reading firmness and origin, recording a person's rule as firm with origin.ref, superseding with a Why this changed section, the kb_compile_intent unresolved/reviewCandidates/conflictReviews loop, asking before overriding a firm rule, putting decisions to the person as one numbered kibi signoff --questions view, and getting a batch of statement changes, splits, reasons or retirements approved during a knowledge base cleanup.

    Raw SKILL.md
  • kibi-freshness

    packages/cursor/skills/kibi-freshness/SKILL.md

    Check exact Git attachment, branch migration/quarantine, compiled-store freshness, source linkage, and repair state before decisions or writes.

    Raw SKILL.md
  • kibi-provable-code

    packages/cursor/skills/kibi-provable-code/SKILL.md

    Use when writing, designing or refactoring code that implements a Kibi requirement (policies, limits, allow-lists, roles, state machines, routes, env and config reads, validators, error types), when a source proof or a value/domain read is refused because Kibi cannot read a name statically (a computed key, a dynamic import or require, eval, reflection, globals()[name], getattr with a computed name, $$var, a macro), or when deciding how to treat generated or vendored code. Covers design practices that make code easier to review, test and replace and that also let Kibi prove claims exactly, the line between a good refactor and a contortion for the tool, the accepted dynamic exceptions (plugins, serialization, registries), and generated code as a boundary.

    Raw SKILL.md
  • kibi-traceability

    packages/cursor/skills/kibi-traceability/SKILL.md

    Maintain source-first requirement, scenario, test, symbol, and proof traceability through Kibi's peer interfaces. Use when linking a code symbol to a requirement (implements, covered_by, executable_for), choosing which function owns a behavior, moving or removing links, or when kb_check reports broad_requirement_review, multi_requirement_symbol_review, coarse_anchor_only_review, symbol-coverage or missing_production_symbol_coverage.

    Raw SKILL.md
  • Kibi Usage

    packages/cursor/skills/kibi-usage/SKILL.md

    Use Kibi's source-first, exact-Git, migration-aware, proof-aware operations safely across MCP or the trusted local CLI, including partial completion repair. Also use for knowledge base quality work: cleaning up or auditing a KB, clearing kibi check review findings (broad_requirement_review, multi_requirement_symbol_review, coarse_anchor_only_review, entity-context-missing), splitting a requirement that covers several behaviors, choosing which function owns a behavior, writing why a requirement exists, and retiring knowledge whose behavior is gone.

    Raw SKILL.md
  • kibi-bootstrap

    packages/runtime/src/skills/kibi-bootstrap/SKILL.md

    Use for any Kibi bootstrap or onboarding task: seeding a new or thin knowledge base; reviewing a bootstrap or onboarding plan, preview, or evidence; judging approval readiness or coverage; diagnosing a blocked, partial, or failed bootstrap or its repair; applying an approved bootstrap plan; or asking the human which knowledge sources hold intent. Covers kb_status first, source interview, cited intent claims, read-only kb_plan_bootstrap preview, explicit approval, exact-plan kb_apply_plan, and repair-safe close-out.

    Raw SKILL.md
  • kibi-commit-review

    packages/runtime/src/skills/kibi-commit-review/SKILL.md

    Use when kibi check --staged or the Kibi pre-commit hook blocks a commit (kibi_impact_evidence_missing, symbols_manifest_stale, symbol_granularity_violation, symbol-coverage, kibi check-generated drift, Staged impact review failed), or when preparing a commit or pull-request impact review. Covers reading the per-file Detail lines, authoring .kb/symbols.yaml symbol entries through kb_upsert, staging the tracked Kibi evidence with git add (symbol coordinates are derived and never staged), kb_prepare_impact_review for a staged or diff scope, the kibi signoff requirements summary to show before a commit, how merge commits and migration renames are judged, and which requirement a newly listed symbol belongs to without making that requirement too broad.

    Raw SKILL.md
  • kibi-decisions

    packages/runtime/src/skills/kibi-decisions/SKILL.md

    Use when the person states a rule or decision (must, never, always, from now on, we decided), when a Kibi hook asks to confirm or warns about an edit to code that implements a firm requirement, when the Stop hook says source files changed but nothing was recorded, when kb_check quotes requirement_statement_unverified, or when a request conflicts with a recorded requirement or ADR. Covers reading firmness and origin, recording a person's rule as firm with origin.ref, superseding with a Why this changed section, the kb_compile_intent unresolved/reviewCandidates/conflictReviews loop, asking before overriding a firm rule, putting decisions to the person as one numbered kibi signoff --questions view, and getting a batch of statement changes, splits, reasons or retirements approved during a knowledge base cleanup.

    Raw SKILL.md
  • kibi-freshness

    packages/runtime/src/skills/kibi-freshness/SKILL.md

    Check exact Git attachment, branch migration/quarantine, compiled-store freshness, source linkage, and repair state before decisions or writes.

    Raw SKILL.md
  • kibi-provable-code

    packages/runtime/src/skills/kibi-provable-code/SKILL.md

    Use when writing, designing or refactoring code that implements a Kibi requirement (policies, limits, allow-lists, roles, state machines, routes, env and config reads, validators, error types), when a source proof or a value/domain read is refused because Kibi cannot read a name statically (a computed key, a dynamic import or require, eval, reflection, globals()[name], getattr with a computed name, $$var, a macro), or when deciding how to treat generated or vendored code. Covers design practices that make code easier to review, test and replace and that also let Kibi prove claims exactly, the line between a good refactor and a contortion for the tool, the accepted dynamic exceptions (plugins, serialization, registries), and generated code as a boundary.

    Raw SKILL.md
  • kibi-traceability

    packages/runtime/src/skills/kibi-traceability/SKILL.md

    Maintain source-first requirement, scenario, test, symbol, and proof traceability through Kibi's peer interfaces. Use when linking a code symbol to a requirement (implements, covered_by, executable_for), choosing which function owns a behavior, moving or removing links, or when kb_check reports broad_requirement_review, multi_requirement_symbol_review, coarse_anchor_only_review, symbol-coverage or missing_production_symbol_coverage.

    Raw SKILL.md
  • Kibi Usage

    packages/runtime/src/skills/kibi-usage/SKILL.md

    Use Kibi's source-first, exact-Git, migration-aware, proof-aware operations safely across MCP or the trusted local CLI, including partial completion repair. Also use for knowledge base quality work: cleaning up or auditing a KB, clearing kibi check review findings (broad_requirement_review, multi_requirement_symbol_review, coarse_anchor_only_review, entity-context-missing), splitting a requirement that covers several behaviors, choosing which function owns a behavior, writing why a requirement exists, and retiring knowledge whose behavior is gone.

    Raw SKILL.md
  • kibi-bootstrap

    packages/zcode/skills/kibi-bootstrap/SKILL.md

    Use for any Kibi bootstrap or onboarding task: seeding a new or thin knowledge base; reviewing a bootstrap or onboarding plan, preview, or evidence; judging approval readiness or coverage; diagnosing a blocked, partial, or failed bootstrap or its repair; applying an approved bootstrap plan; or asking the human which knowledge sources hold intent. Covers kb_status first, source interview, cited intent claims, read-only kb_plan_bootstrap preview, explicit approval, exact-plan kb_apply_plan, and repair-safe close-out.

    Raw SKILL.md
  • kibi-commit-review

    packages/zcode/skills/kibi-commit-review/SKILL.md

    Use when kibi check --staged or the Kibi pre-commit hook blocks a commit (kibi_impact_evidence_missing, symbols_manifest_stale, symbol_granularity_violation, symbol-coverage, kibi check-generated drift, Staged impact review failed), or when preparing a commit or pull-request impact review. Covers reading the per-file Detail lines, authoring .kb/symbols.yaml symbol entries through kb_upsert, staging the tracked Kibi evidence with git add (symbol coordinates are derived and never staged), kb_prepare_impact_review for a staged or diff scope, the kibi signoff requirements summary to show before a commit, how merge commits and migration renames are judged, and which requirement a newly listed symbol belongs to without making that requirement too broad.

    Raw SKILL.md
  • kibi-decisions

    packages/zcode/skills/kibi-decisions/SKILL.md

    Use when the person states a rule or decision (must, never, always, from now on, we decided), when a Kibi hook asks to confirm or warns about an edit to code that implements a firm requirement, when the Stop hook says source files changed but nothing was recorded, when kb_check quotes requirement_statement_unverified, or when a request conflicts with a recorded requirement or ADR. Covers reading firmness and origin, recording a person's rule as firm with origin.ref, superseding with a Why this changed section, the kb_compile_intent unresolved/reviewCandidates/conflictReviews loop, asking before overriding a firm rule, putting decisions to the person as one numbered kibi signoff --questions view, and getting a batch of statement changes, splits, reasons or retirements approved during a knowledge base cleanup.

    Raw SKILL.md
  • kibi-freshness

    packages/zcode/skills/kibi-freshness/SKILL.md

    Check exact Git attachment, branch migration/quarantine, compiled-store freshness, source linkage, and repair state before decisions or writes.

    Raw SKILL.md
  • kibi-provable-code

    packages/zcode/skills/kibi-provable-code/SKILL.md

    Use when writing, designing or refactoring code that implements a Kibi requirement (policies, limits, allow-lists, roles, state machines, routes, env and config reads, validators, error types), when a source proof or a value/domain read is refused because Kibi cannot read a name statically (a computed key, a dynamic import or require, eval, reflection, globals()[name], getattr with a computed name, $$var, a macro), or when deciding how to treat generated or vendored code. Covers design practices that make code easier to review, test and replace and that also let Kibi prove claims exactly, the line between a good refactor and a contortion for the tool, the accepted dynamic exceptions (plugins, serialization, registries), and generated code as a boundary.

    Raw SKILL.md
  • kibi-traceability

    packages/zcode/skills/kibi-traceability/SKILL.md

    Maintain source-first requirement, scenario, test, symbol, and proof traceability through Kibi's peer interfaces. Use when linking a code symbol to a requirement (implements, covered_by, executable_for), choosing which function owns a behavior, moving or removing links, or when kb_check reports broad_requirement_review, multi_requirement_symbol_review, coarse_anchor_only_review, symbol-coverage or missing_production_symbol_coverage.

    Raw SKILL.md
  • Kibi Usage

    packages/zcode/skills/kibi-usage/SKILL.md

    Use Kibi's source-first, exact-Git, migration-aware, proof-aware operations safely across MCP or the trusted local CLI, including partial completion repair. Also use for knowledge base quality work: cleaning up or auditing a KB, clearing kibi check review findings (broad_requirement_review, multi_requirement_symbol_review, coarse_anchor_only_review, entity-context-missing), splitting a requirement that covers several behaviors, choosing which function owns a behavior, writing why a requirement exists, and retiring knowledge whose behavior is gone.

    Raw SKILL.md

File inventory

.agents/plugins/marketplace.json

file

429 bytes

136bfed3d0797b52…

.agents/skills/open-code-review-delegate/SKILL.md

skill

7,966 bytes

20828a50b0546549…

.claude-plugin/marketplace.json

file

1,135 bytes

c9e9d51466af8793…

.codex-plugin/plugin.json

plugin-manifest

1,496 bytes

bf2211c3cb2ea63b…

.cursor-plugin/marketplace.json

file

1,581 bytes

932ff1d0aa34a240…

.cursor/mcp.json

file

192 bytes

713a52943a0ef5b4…

.cursor/rules/kibi-traceability.mdc

file

915 bytes

23f5c58d717e2899…

.cursor/rules/kibi-workflow.mdc

file

1,955 bytes

d2c63f90b02b8e8c…

.github/dependabot.yml

file

789 bytes

47c7a8735d31238d…

.mcp.json

file

232 bytes

cb1c7444c1db3596…

.opencode/plugins/kibi.ts

file

130 bytes

0118b3ae1988f8bc…

.opencode/plugins/kibi.tui.ts

file

63 bytes

f49c19c6229d3b3b…

.registry/mcp.json

mcp-config

205 bytes

63277c0c4d76e075…

.vscode/mcp.json

file

266 bytes

7f1ad94e1f88ec65…

AGENTS.md

file

9,843 bytes

e32cd42ff98e35be…

biome.json

file

601 bytes

0fa18a09dba21139…

documentation/evaluations/skillopt/proposals/2026-10-04/kibi-freshness/SKILL.md

skill

4,863 bytes

290d361ade71096d…

documentation/evaluations/skillopt/proposals/2026-10-20/kibi-freshness/SKILL.md

skill

5,297 bytes

998cb9df3e6d663e…

documentation/evaluations/skillopt/proposals/2026-10-20/kibi-traceability/SKILL.md

skill

3,902 bytes

bc866eb2dd083f80…

documentation/evaluations/skillopt/proposals/2026-10-20/kibi-usage/SKILL.md

skill

36,060 bytes

86528127198ff13d…

documentation/evaluations/skillopt/proposals/2026-10-21/kibi-freshness/SKILL.md

skill

5,455 bytes

f1ccfa35dae113d7…

documentation/evaluations/skillopt/proposals/2026-10-21/kibi-traceability/SKILL.md

skill

3,805 bytes

49a17392c63997db…

documentation/evaluations/skillopt/proposals/2026-10-21b/kibi-traceability/SKILL.md

skill

5,225 bytes

f4ebc9a57dae6fcb…

documentation/evaluations/skillopt/proposals/2026-10-22/kibi-usage/SKILL.md

skill

35,437 bytes

90622e5ecda235d1…

documentation/evaluations/skillopt/proposals/2026-10-22b/kibi-commit-review/SKILL.md

skill

6,693 bytes

03a0d72bd5b8ac6d…

documentation/evaluations/skillopt/proposals/2026-10-22c/kibi-decisions/SKILL.md

skill

8,409 bytes

d49784d19dfb6056…

documentation/evaluations/skillopt/proposals/2026-10-22d/kibi-usage/SKILL.md

skill

36,422 bytes

b874453edf3794e3…

LICENSE

file

46,028 bytes

9c77236292010f97…

LICENSE.md

file

34,519 bytes

068de0a1cda6e78f…

opencode.json

file

622 bytes

326d3e8effe93762…

package.json

file

10,776 bytes

e0ce5174206aa577…

packages/claude/skills/kibi-bootstrap/resources/bootstrap.md

file

1,976 bytes

cb61dcb629d9f631…

packages/claude/skills/kibi-bootstrap/resources/branch-lifecycle.md

file

401 bytes

c854264ce8884391…

packages/claude/skills/kibi-bootstrap/resources/operation-access.md

file

242 bytes

b5a6a59e72d800c3…

packages/claude/skills/kibi-bootstrap/resources/source-authoring.md

file

392 bytes

bf296e62f69474e0…

packages/claude/skills/kibi-bootstrap/SKILL.md

skill

19,335 bytes

942417ea4365d776…

packages/claude/skills/kibi-commit-review/resources/staged-gate.md

file

11,420 bytes

683c491b8bb59fa5…

packages/claude/skills/kibi-commit-review/SKILL.md

skill

9,150 bytes

73031902ed6f6bf7…

packages/claude/skills/kibi-decisions/resources/decision-records.md

file

11,502 bytes

f6696237a46cda6f…

packages/claude/skills/kibi-decisions/resources/signoff-views.md

file

4,186 bytes

84eb2b7123e54047…

packages/claude/skills/kibi-decisions/SKILL.md

skill

14,192 bytes

abc91d6e392b3cd1…

packages/claude/skills/kibi-freshness/resources/branch-lifecycle.md

file

306 bytes

ebc01b19fe3dca8d…

packages/claude/skills/kibi-freshness/resources/operation-access.md

file

246 bytes

4e1db9294ee540cd…

packages/claude/skills/kibi-freshness/resources/source-authoring.md

file

275 bytes

41a0547ce4d2a112…

packages/claude/skills/kibi-freshness/SKILL.md

skill

6,393 bytes

3dd372a4baf6705f…

packages/claude/skills/kibi-provable-code/resources/provable-patterns.md

file

5,376 bytes

85436ab68a845837…

packages/claude/skills/kibi-provable-code/SKILL.md

skill

11,515 bytes

efead5a7a475cf9d…

packages/claude/skills/kibi-traceability/resources/branch-lifecycle.md

file

285 bytes

50f1a6355aa9185d…

packages/claude/skills/kibi-traceability/resources/operation-access.md

file

260 bytes

39f7972ab7f4ae74…

packages/claude/skills/kibi-traceability/resources/source-authoring.md

file

253 bytes

408c6ee2bef1b84e…

packages/claude/skills/kibi-traceability/resources/traceability.md

file

1,021 bytes

5c6a7bb76c8e37da…

packages/claude/skills/kibi-traceability/SKILL.md

skill

9,001 bytes

72bd471873853892…

packages/claude/skills/kibi-usage/resources/branch-lifecycle.md

file

1,933 bytes

f1bf359e9826e83c…

packages/claude/skills/kibi-usage/resources/domain-subjects.md

file

4,824 bytes

d6218b334f9cad8e…

packages/claude/skills/kibi-usage/resources/fact-lanes.md

file

17,555 bytes

4406857ca3760b72…

packages/claude/skills/kibi-usage/resources/hook-snippets.md

file

2,583 bytes

e44c51ed8995229b…

packages/claude/skills/kibi-usage/resources/interfaces.md

file

4,137 bytes

ceeadaacd46aabb0…

packages/claude/skills/kibi-usage/resources/kb-improvement.md

file

1,940 bytes

82eb3354ab47e39f…

packages/claude/skills/kibi-usage/resources/kb-quality.md

file

10,820 bytes

057988528b644a0e…

packages/claude/skills/kibi-usage/resources/logic-ir.md

file

4,548 bytes

9a125adaf380043e…

packages/claude/skills/kibi-usage/resources/operation-access.md

file

7,208 bytes

f8ee3b21c3abb1ac…

packages/claude/skills/kibi-usage/resources/operation-fields.md

file

43,631 bytes

df8bb6d748053c49…

packages/claude/skills/kibi-usage/resources/predicate-ontology.md

file

7,315 bytes

9e241ac2eeaf51fd…

packages/claude/skills/kibi-usage/resources/prolog-proofs.md

file

10,193 bytes

b630f1edf32c4d14…

packages/claude/skills/kibi-usage/resources/proof.md

file

32,200 bytes

6f2c22e841f5ba63…

packages/claude/skills/kibi-usage/resources/quantified-claims.md

file

2,350 bytes

b6f20041f473e793…

packages/claude/skills/kibi-usage/resources/recording.md

file

13,286 bytes

8d071409a5aeb412…

packages/claude/skills/kibi-usage/resources/relationship-directions.md

file

4,763 bytes

f0e6c0b147233b0d…

packages/claude/skills/kibi-usage/resources/requirement-size.md

file

5,329 bytes

aae38773d8d982c6…

packages/claude/skills/kibi-usage/resources/results-and-recovery.md

file

4,267 bytes

06254656f14551c5…

packages/claude/skills/kibi-usage/resources/second-agent-edits.md

file

7,404 bytes

1123bbb20987e51d…

packages/claude/skills/kibi-usage/resources/source-authoring.md

file

4,316 bytes

0ad85fd25667ef0b…

packages/claude/skills/kibi-usage/resources/ui-requirements.md

file

6,374 bytes

1c3de8e91eb1e79a…

packages/claude/skills/kibi-usage/resources/workflows.md

file

20,743 bytes

b2f65ba058c7a2c2…

packages/claude/skills/kibi-usage/SKILL.md

skill

5,327 bytes

a438e1ffefe3f008…

packages/cli/src/public/skills/kibi-bootstrap/resources/bootstrap.md

file

1,976 bytes

cb61dcb629d9f631…

packages/cli/src/public/skills/kibi-bootstrap/resources/branch-lifecycle.md

file

401 bytes

c854264ce8884391…

packages/cli/src/public/skills/kibi-bootstrap/resources/operation-access.md

file

242 bytes

b5a6a59e72d800c3…

packages/cli/src/public/skills/kibi-bootstrap/resources/source-authoring.md

file

392 bytes

bf296e62f69474e0…

packages/cli/src/public/skills/kibi-bootstrap/SKILL.md

skill

19,242 bytes

764c1214836d8574…

packages/cli/src/public/skills/kibi-commit-review/resources/staged-gate.md

file

11,420 bytes

683c491b8bb59fa5…

packages/cli/src/public/skills/kibi-commit-review/SKILL.md

skill

9,057 bytes

59e104bba5b474aa…

packages/cli/src/public/skills/kibi-decisions/resources/decision-records.md

file

11,502 bytes

f6696237a46cda6f…

packages/cli/src/public/skills/kibi-decisions/resources/signoff-views.md

file

4,186 bytes

84eb2b7123e54047…

packages/cli/src/public/skills/kibi-decisions/SKILL.md

skill

14,101 bytes

70496cba0a2c5c25…

packages/cli/src/public/skills/kibi-freshness/resources/branch-lifecycle.md

file

306 bytes

ebc01b19fe3dca8d…

packages/cli/src/public/skills/kibi-freshness/resources/operation-access.md

file

246 bytes

4e1db9294ee540cd…

packages/cli/src/public/skills/kibi-freshness/resources/source-authoring.md

file

275 bytes

41a0547ce4d2a112…

packages/cli/src/public/skills/kibi-freshness/SKILL.md

skill

6,302 bytes

fe9f7c3c16a29475…

packages/cli/src/public/skills/kibi-provable-code/resources/provable-patterns.md

file

5,376 bytes

85436ab68a845837…

packages/cli/src/public/skills/kibi-provable-code/SKILL.md

skill

11,422 bytes

4fbe20c2ec335848…

packages/cli/src/public/skills/kibi-traceability/resources/branch-lifecycle.md

file

285 bytes

50f1a6355aa9185d…

packages/cli/src/public/skills/kibi-traceability/resources/operation-access.md

file

260 bytes

39f7972ab7f4ae74…

packages/cli/src/public/skills/kibi-traceability/resources/source-authoring.md

file

253 bytes

408c6ee2bef1b84e…

packages/cli/src/public/skills/kibi-traceability/resources/traceability.md

file

1,021 bytes

5c6a7bb76c8e37da…

packages/cli/src/public/skills/kibi-traceability/SKILL.md

skill

8,903 bytes

ef509f2cc2ddce09…

packages/cli/src/public/skills/kibi-usage/resources/branch-lifecycle.md

file

1,933 bytes

f1bf359e9826e83c…

packages/cli/src/public/skills/kibi-usage/resources/domain-subjects.md

file

4,824 bytes

d6218b334f9cad8e…

packages/cli/src/public/skills/kibi-usage/resources/fact-lanes.md

file

17,555 bytes

4406857ca3760b72…

packages/cli/src/public/skills/kibi-usage/resources/hook-snippets.md

file

2,583 bytes

e44c51ed8995229b…

Browse all 342 files

kibi — Frequently asked questions

What is kibi?
kibi is an AI plugin in the HOL registry. MCP server and per-agent plugins that compile product intent into structured requirements and check that code and tests stay consistent with them.
How do I install kibi?
Install kibi in your harness: Source — https://github.com/Looted/kibi/releases; Any agent — npx [email protected] add Looted/kibi. Full step-by-step guidance is on the HOL plugin page.
How do I install kibi in Source?
To install kibi in Source, start with https://github.com/Looted/kibi/releases. The complete step-by-step install guide for Source is on the HOL plugin page.
How is the Trust Score for kibi computed?
kibi has a HOL Trust Score of 77 out of 100. The score is a weighted sum of six components from a static scan of the source, capped for high-severity findings and adjusted by two disclosed policies. Memberships and payments are not inputs, and a scan is not a safety guarantee. Full breakdown: https://hol.org/registry/plugins/looted%2Fkibi/trust
Who publishes kibi?
kibi is published by Looted and listed on HOL.

Directory acceptance

Listed in 0 of 5 directory lists

Read from the list each directory publishes on GitHub. Being listed means the directory accepted the plugin; it is not a HOL security rating.

Lists last read . HOL re-reads them every day.

Submitting it? Check it against each directory's rules

Install signal

HOL cannot see every install. These are separate signals from different sources, so they are not added together. Counts under each floor show as <N.

Install commands issued here
<5
HOL Guard install commands issued from this listing, last 28 days.
Opt-in install reports
<10
Machines that reported installing it through HOL Guard in week 2026-W46. Reporting is opt-in, so most installs are not counted.
HOL Guard workspaces
<5
Workspaces that approved it or include it in an approved-plugin feed, as of today.
New GitHub stars
<5
From HOL's GitHub snapshots of the repository, 2026-10-23 to 2026-11-20.

Reviews and similar plugins