Agent Harness Skills icon

Agent Harness Skills

agent-harness-skills-contributors/agent-harness-skills · v0.2.1 · Development & Workflow

Designs agent-ready repository harnesses with entrypoints, validation surfaces, runtime evidence, delivery records, and atomic commit guidance.

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 Agent Harness Skills a fit?

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

Works with

  • Codex
  • Claude Code
  • Antigravity CLI
  • Cursor
  • 5 skills

Before you install

Sign-in
Asks you to sign in when you install it
Declared access
Interactive, Read, Write
License
MIT

Check before relying on it

  • Some security checks did not finish: Cisco skill scan. See the evidence
  • The publisher has not verified ownership on HOL.

What is Agent Harness Skills?

Agent Harness Skills is a published development & workflow plugin for AI coding agents that works with Codex, Claude Code, Antigravity CLI and Cursor, developed by Agent Harness Skills contributors and distributed through the HOL AI plugin registry. Designs agent-ready repository harnesses with entrypoints, validation surfaces, runtime evidence, delivery records, and atomic commit guidance.

Canonical slug
agent-harness-skills-contributors/agent-harness-skills
Version
v0.2.1 · updated Nov 5, 2026

Registry snapshot

Owner verification
Not verified
Scanner
HOL plugin scanner
Security result
Partial scan
Digest verified
Yes
5 bundled skillsRead, copy or download each SKILL.mdOpen skills

Trust and security

Trust & reputation

88

HOL Trust Score

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

Installability
100/100
Maintenance
100/100
MCP server setup
100/100
Plugin Security
91/100
Provenance
70/100
Publisher Quality
75/100

Provenance

Plugin root
.
Source repo
https://github.com/yfge/agent-harness-skills
Source commit
a91757d3a0d0…
Publisher verified
No
Owner verified
Not owner verified
Agent Plugins 1.0
Not detected

Continuous scanner CI detected

No action is required. This plugin receives the full trust score.

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.

Partial scan
Security result
91
Score from finished checks
0
High findings

Some checks did not finish: Cisco skill scan. No blocking issue was found in the checks that did finish, but this is not a passed scan.

Provider
codex-plugin-scanner
Grade
A · Excellent
Version
3.24.2
codex:hol-plugin-scanner-Win3d8 / cisco-skill-scanner: failedcodex:hol-plugin-scanner-Win3d8 / cisco-mcp-scanner: skipped

[claude:.] Claude Plugin

18/18

5 checks

[claude:.] Security

16/16

6 checks

[claude:.] Operational Security

3/6

5 checks

[claude:.] Code Quality

10/10

2 checks

[codex:.] Manifest Validation

28/31

9 checks

[codex:.] Security

16/16

9 checks

[codex:.] Operational Security

3/6

5 checks

[codex:.] Best Practices

9/12

5 checks

[codex:.] Marketplace

N/A

3 checks · not applicable

[codex:.] Skill Security

5/5

4 checks

[codex:.] Code Quality

10/10

2 checks

[gemini:.] Gemini Extension

10/10

3 checks

[gemini:.] Security

16/16

6 checks

[gemini:.] Operational Security

3/6

5 checks

[gemini:.] Code Quality

10/10

2 checks

[opencode:.] OpenCode Plugin

2/2

4 checks

[opencode:.] Security

16/16

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

lowoperational-securityDEPENDABOT_MISSINGReported 4 times

Automation or dependency surfaces exist, but .github/dependabot.yml is missing.

Add Dependabot updates for GitHub Actions and dependency manifests.

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_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 Claude Code

Install through the Claude Code plugin marketplace.

Claude Code plugin docs

Optional: install HOL Guard for Claude Code first, so it can check this plugin's tools on your machine before Claude Code uses them.

  1. 1

    Add the marketplace

    Run this inside a Claude Code session. It registers the marketplace manifest shipped at the repository root. If the repository ships none, add the generated entry from the Advanced section below first.

    claude code
  2. 2

    Find the marketplace and plugin names

    The install id is <plugin-entry>@<marketplace-name>, and the marketplace name is declared inside the manifest — it can differ from the repository name. List registered marketplaces to read both names.

    shell
  3. 3

    Install the plugin

    Substitute the plugin entry name and the marketplace name shown by the previous step.

    claude code

Did setup work in Claude Code?

No setup reports for Claude Code 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

{
  "id": "agent-harness-skills",
  "name": "agent-harness-skills",
  "version": "0.2.1",
  "description": "Reusable skills for building agent-ready repository harnesses.",
  "author": {
    "name": "Agent Harness Skills contributors"
  },
  "homepage": "https://github.com/yfge/agent-harness-skills",
  "repository": "https://github.com/yfge/agent-harness-skills",
  "license": "MIT",
  "skills": "./",
  "interface": {
    "displayName": "Agent Harness Skills",
    "developerName": "Agent Harness Skills contributors",
    "shortDescription": "Repo harness practices for agent-ready engineering work",
    "longDescription": "Use Agent Harness Skills as a compact methodology plugin to assess and design repository harnesses: entrypoint and role mapping, mechanical contracts, structural quality, validation surfaces, runtime evidence, and optional work-state and delivery governance.",
    "category": "Coding",
    "websiteURL": "https://github.com/yfge/agent-harness-skills",
    "brandColor": "#2F6FED",
    "composerIcon": "./assets/icon.svg",
    "capabilities": [
      "Interactive",
      "Read",
      "Write"
    ],
    "defaultPrompt": "Assess this repository's agent harness maturity."
  },
  "keywords": [
    "agent-harness",
    "skills",
    "repository",
    "validation",
    "codex-plugin",
    "methodology",
    "templates",
    "runtime-evidence",
    "delivery"
  ],
  "holManifestOrigin": "repository",
  "registryIndexVersion": 9
}

Marketplace source

Repo URL
https://github.com/yfge/agent-harness-skills
Marketplace path
Unknown
Source path
plugins/yfge/agent-harness-skills
Install policy
AVAILABLE

Skills

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

Share
skills-cli
  • repo-contracts-and-boundaries

    skills/repo-contracts-and-boundaries/SKILL.md

    Use when turning architecture, layering, ownership, dependency direction, schemas, structural metrics, quality thresholds, baselines, allowlists, or generated quality snapshots into repository checks.

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • repo-harness-assessment

    skills/repo-harness-assessment/SKILL.md

    Use when evaluating repository agent-readiness, mapping harness roles, choosing the next smallest improvement, or designing and reconciling agent entrypoints such as AGENTS.md, CLAUDE.md, GEMINI.md, Cursor rules, or GitHub instructions.

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • runtime-evidence-and-tracing

    skills/runtime-evidence-and-tracing/SKILL.md

    Use when connecting observed behavior, logs, metrics, request IDs, run IDs, screenshots, traces, external dependency results, or artifacts into a runtime evidence loop.

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • validation-harness-design

    skills/validation-harness-design/SKILL.md

    Use when designing repository validation commands, doctor scripts, test matrices, JSON or JUnit outputs, CI gates, smoke checks, or harness command surfaces.

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • work-state-and-delivery

    skills/work-state-and-delivery/SKILL.md

    Use when designing or reconciling design docs, task boards, external trackers, execution plans, delivery records, handoffs, review evidence, task-to-change traceability, or repository commit-coupling policy.

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

File inventory

.claude-plugin/plugin.json

file

486 bytes

24fe932f996dfd1a…

.codex-plugin/plugin.json

plugin-manifest

1,261 bytes

1d734d044728d172…

.cursor-plugin/plugin.json

file

552 bytes

327b26155aff0da3…

.opencode/plugins/agent-harness-skills.js

file

2,898 bytes

23070fb0b0d82bf5…

AGENTS.md

file

2,313 bytes

27ff4ec3db8881dc…

assets/icon.svg

asset

711 bytes

a3e315214559e84d…

gemini-extension.json

file

176 bytes

73215bd9ff7b4e84…

GEMINI.md

file

627 bytes

1142402c575a4313…

LICENSE

file

1,456 bytes

f0ebe427f8bd1289…

package-lock.json

file

227 bytes

af23f3b98db05b4d…

package.json

file

1,192 bytes

26f53cfb9d2f216a…

README.md

file

12,400 bytes

364cff3a0303146c…

SECURITY.md

file

1,546 bytes

cec19fe34602a282…

skills/repo-contracts-and-boundaries/references/build-when-missing.md

skill

2,349 bytes

73d533097f80d40c…

skills/repo-contracts-and-boundaries/references/quality-policy.md

skill

1,533 bytes

14646a20ca1292c5…

skills/repo-contracts-and-boundaries/references/schema-fixture-contracts.md

skill

1,149 bytes

ea4cc4c4f8419a41…

skills/repo-contracts-and-boundaries/SKILL.md

skill

4,651 bytes

1a778263544680f1…

skills/repo-harness-assessment/references/build-when-missing.md

skill

2,485 bytes

c6d1c893db69b05a…

skills/repo-harness-assessment/references/entrypoint-policy.md

skill

1,403 bytes

304497fcd362c46b…

skills/repo-harness-assessment/SKILL.md

skill

5,222 bytes

d7269a398c6851f8…

skills/runtime-evidence-and-tracing/references/build-when-missing.md

skill

2,086 bytes

96a19a25f3c19518…

skills/runtime-evidence-and-tracing/references/runtime-profile-policy.md

skill

1,111 bytes

3517cc88394f6c5c…

skills/runtime-evidence-and-tracing/SKILL.md

skill

3,810 bytes

86930b954966125a…

skills/validation-harness-design/references/build-when-missing.md

skill

2,024 bytes

2552fcad8f26684c…

skills/validation-harness-design/references/environment-bootstrap.md

skill

1,086 bytes

35022f6fb190be88…

skills/validation-harness-design/SKILL.md

skill

3,476 bytes

3efeb80dd75f1e49…

skills/work-state-and-delivery/references/build-when-missing.md

skill

2,303 bytes

8d5b80c27d0b3b5b…

skills/work-state-and-delivery/references/delivery-and-commit-policy.md

skill

1,918 bytes

41be0a1b37ed1c02…

skills/work-state-and-delivery/SKILL.md

skill

5,145 bytes

c3d7a4c82d502b6e…

Agent Harness Skills — Frequently asked questions

What is Agent Harness Skills?
Agent Harness Skills is an AI plugin in the HOL registry. Designs agent-ready repository harnesses with entrypoints, validation surfaces, runtime evidence, delivery records, and atomic commit guidance.
How do I install Agent Harness Skills?
Install Agent Harness Skills in your harness: Codex — codex plugin marketplace add yfge/agent-harness-skills; Claude Code — /plugin marketplace add yfge/agent-harness-skills; Cursor — npx [email protected] add yfge/agent-harness-skills. Full step-by-step guidance is on the HOL plugin page.
How do I install Agent Harness Skills in Codex?
To install Agent Harness Skills in Codex, start with codex plugin marketplace add yfge/agent-harness-skills. The complete step-by-step install guide for Codex is on the HOL plugin page.
How do I install Agent Harness Skills in Claude Code?
To install Agent Harness Skills in Claude Code, start with /plugin marketplace add yfge/agent-harness-skills. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
How do I install Agent Harness Skills in Cursor?
To install Agent Harness Skills in Cursor, start with npx [email protected] add yfge/agent-harness-skills. The complete step-by-step install guide for Cursor is on the HOL plugin page.
How is the Trust Score for Agent Harness Skills computed?
Agent Harness Skills has a HOL Trust Score of 88 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/agent-harness-skills-contributors%2Fagent-harness-skills/trust
Who publishes Agent Harness Skills?
Agent Harness Skills is published by Agent Harness Skills contributors and listed on HOL.

Directory acceptance

Listed in 1 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.

Reviews and similar plugins