hiway-kit icon

hiway-kit

this-hw/hiway-kit · v5.7.1 · Development & Workflow

by This-HWScan grade: GoodAwesome AI Plugins

Discipline kit for coding agents with 17 skills for planning, automated implementation, testing, debugging, review and multi-session coordination, where work counts as done only when the project's own checks pass.

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 hiway-kit 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
  • Cursor
  • Agent Plugin
  • 17 skills
  • Runs hooks on agent events

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 hiway-kit?

hiway-kit is a published development & workflow plugin for AI coding agents that works with Codex, Claude Code, Cursor and Agent Plugin, developed by This-HW and distributed through the HOL AI plugin registry. Discipline kit for coding agents with 17 skills for planning, automated implementation, testing, debugging, review and multi-session coordination, where work counts as done only when the project's own checks pass.

Canonical slug
this-hw/hiway-kit
Version
v5.7.1 · updated Nov 11, 2026

Registry snapshot

Owner verification
Not verified
Marketplace source
.claude-plugin/marketplace.json
Scanner
HOL plugin scanner
Security result
Needs review
Digest verified
Yes
17 bundled skillsRead, copy or download each SKILL.mdOpen skills

Trust and security

Trust & reputation

74

HOL Trust Score

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

Installability
100/100
Maintenance
30/100
MCP server setup
100/100
Plugin Security
85/100
Provenance
70/100
Publisher Quality
75/100

Provenance

Plugin root
plugins/common
Source repo
https://github.com/This-HW/hiway-kit
Source commit
82f0cd38f8aa…
Publisher verified
No
Owner verified
Not owner verified
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-32cKTO / cisco-skill-scanner: failedcodex:hol-plugin-scanner-32cKTO / cisco-mcp-scanner: skipped

[claude:.] Claude Plugin

18/18

5 checks

[claude:.] Security

10/16

6 checks

[claude:.] Operational Security

N/A

5 checks · not applicable

[claude:.] Code Quality

10/10

2 checks

[codex:.] Manifest Validation

28/31

9 checks

[codex:.] Security

10/16

9 checks

[codex:.] Operational Security

N/A

5 checks · not applicable

[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

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

lowsecuritySECURITY_MD_MISSINGReported 2 times

Plugins should publish a SECURITY.md file for responsible disclosure and support guidance.

Add a SECURITY.md file with reporting guidance and supported versions.

lowsecurityLICENSE_MISSINGReported 2 times

Plugins should ship a LICENSE file so consumers can review usage rights.

Add a LICENSE file that matches the manifest license metadata.

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

    Install the plugin

    Installs the hiway-kit entry from the hiway-kit marketplace.

    claude code
  3. 3

    Scripted alternative

    Non-interactive equivalent for scripts and CI pipelines. Add --scope project to pin the install to one repository.

    shell
  4. 4

    Check it is installed

    Lists installed plugins. The entry should appear as enabled.

    shell

To remove it later, run claude plugin uninstall hiway-kit@hiway-kit.

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

{
  "author": {
    "email": "[email protected]",
    "name": "This-HW",
    "url": "https://github.com/This-HW"
  },
  "description": "Turn any task into production-ready code. Rules and skills work on any coding harness; specialized agents and automatic hook enforcement are a Claude Code deepening feature.",
  "homepage": "https://hiway.thishw.com/",
  "hooks": "./hooks/hooks-codex.json",
  "interface": {
    "displayName": "hiway-kit",
    "developerName": "This-HW",
    "capabilities": [
      "Interactive",
      "Read",
      "Write"
    ],
    "category": "Developer Tools",
    "composerIcon": "./assets/icon.png",
    "logo": "./assets/icon.png",
    "longDescription": "hiway-kit is a discipline kit for coding agents. Its 17 skills turn a request into verified, production-ready code.\n\n- Planning: plan-task writes a plan file with executable done-criteria; brainstorming handles design for large new features.\n- Execution: auto-dev runs a plan through implementation and validation; test and debug run the tests, diagnose failures and fix them.\n- Review: review runs lint, an adversarial code review and a security scan; multi-perspective-review and cross-engine-review reach an evidence-backed decision across perspectives or across agent engines.\n- Coordination: control-loop and child-session keep multi-session work safe with clear briefs, isolated branches and verification before merge.\n- Code intelligence: code-intel provides AST search, replacement previews and one-shot LSP queries; session-history searches explicitly selected local logs.\n- Knowledge: web-research, skill-forge (turn a solved problem into a reusable skill), agent-creator, and harness-export (share the kit's rules with other coding agents through AGENTS.md).\n\nDone is judged by command output, not by claims: the skills tell the agent to run the project's own tests and checks before reporting work as finished.\n\nThe kit has no telemetry or publisher service. Local helpers can read selected code and session logs and invoke installed tools. Language servers and project tools may execute workspace code, write files or access the network; use code intelligence only in trusted workspaces. Skills that search the web use the tools you already have.",
    "privacyPolicyURL": "https://hiway.thishw.com/privacy/",
    "shortDescription": "Coding agent discipline kit",
    "supportURL": "https://github.com/This-HW/hiway-kit/issues",
    "termsOfServiceURL": "https://github.com/This-HW/hiway-kit/blob/main/LICENSE",
    "websiteURL": "https://hiway.thishw.com/"
  },
  "keywords": [
    "agents",
    "skills",
    "development",
    "planning",
    "review",
    "tdd",
    "debugging"
  ],
  "license": "MIT",
  "name": "hiway-kit",
  "repository": "https://github.com/This-HW/hiway-kit",
  "skills": "./",
  "version": "5.7.1",
  "holManifestOrigin": "repository",
  "registryIndexVersion": 9
}

Marketplace source

Repo URL
https://github.com/This-HW/hiway-kit
Marketplace path
.claude-plugin/marketplace.json
Source path
plugins/This-HW/hiway-kit
Install policy
AVAILABLE

Skills

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

Share
skills-cli
  • agent-creator

    skills/agent-creator/SKILL.md

    Create a Claude Code sub-agent definition for this project or user. Use when the user asks to create a new custom agent or a specialized sub-agent for a recurring task.

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

  • auto-dev

    skills/auto-dev/SKILL.md

    Automated development pipeline. Runs a completed plan file through Development and Validation phases end-to-end.

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

  • brainstorming

    skills/brainstorming/SKILL.md

    Design and spec a Large new feature or system change before planning - explores requirements, proposes approaches, gets design approval, then chains to plan-task. Skip for bug fixes and Small/Medium work; go straight to plan-task or just do it.

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

  • child-session

    skills/child-session/SKILL.md

    Discipline a worker session loads at dispatch time — verify the brief's premises before implementing, work only on its own branch, and report in the fixed completion format. Use when a session has been dispatched as a worker (child) with a brief from a parent control session.

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

  • code-intel

    skills/code-intel/SKILL.md

    Use AST search, replacement previews, and language-server diagnostics or navigation in trusted workspaces; servers may execute project code. Choose AST for code structure, LSP for semantic questions, and text search for literal strings.

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

  • control-loop

    skills/control-loop/SKILL.md

    Multi-session control discipline for delegating work to worker sessions — investigate, decide, dispatch, verify, and merge. Use when a session is coordinating separate worker sessions or worktrees and needs to know when to delegate versus decide, and how to verify before merging.

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

  • cross-engine-review

    skills/cross-engine-review/SKILL.md

    Reach an evidence-backed decision between sessions running on different agent engines. Use when a call is high-stakes enough that one engine's blind spots are a real risk, and a second session with different tool access can bring evidence the first cannot.

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

  • debug

    skills/debug/SKILL.md

    Investigate a failure whose cause is not evident from the error itself - flaky or intermittent failures, failures that only happen in CI or one environment, or errors with several plausible causes across files - by reproducing, isolating, fixing and verifying. Skip it when the message already shows the fix (a missing variable, a typo, a wrong import); just fix that directly.

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

  • harness-export

    skills/harness-export/SKILL.md

    Export the kit's host-neutral rules to every harness entrypoint file (AGENTS.md, GEMINI.md) so non-Claude-Code harnesses (Codex, OpenCode, Copilot, Gemini CLI, Pi, Hermes) follow the same discipline. Use when a repo is worked by more than one agent harness, or after changing rules/. Trigger with /harness-export.

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

  • multi-perspective-review

    skills/multi-perspective-review/SKILL.md

    Multi-perspective review of a plan or design document. Up to ten viewpoints deliberate in 3 rounds; the main session orchestrates, with a sequential path for harnesses without subagents.

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

  • plan-task

    skills/plan-task/SKILL.md

    Structured task planning into a plan file. Use for any new feature, bug fix, or project that needs a task breakdown before implementation.

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

  • review

    skills/review/SKILL.md

    Review current changes or specified files - ruff lint for Python files, an adversarial review-code pass, and a security scan only when security-sensitive files changed.

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

  • session-history

    skills/session-history/SKILL.md

    Search explicitly selected local Codex or Claude JSONL session logs to recover past work with source file and line evidence. Use when the user asks about earlier coding sessions or decisions.

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

  • skill-forge

    skills/skill-forge/SKILL.md

    Distill a hard problem you just solved into a reusable skill draft - proposal-only, behind a three-condition threshold. Use after finishing a non-trivial task whose procedure would otherwise die with the session. Trigger with /skill-forge.

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

  • test

    skills/test/SKILL.md

    Run tests and auto-fix failures. Detects the test framework, executes tests, and iterates on fixes until all pass.

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

  • using-hiway-kit

    skills/using-hiway-kit/SKILL.md

    Session-start meta-skill (hook-injected). Kit workflow chain and plan file rules.

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

  • web-research

    skills/web-research/SKILL.md

    Multi-source external research with cited sources, using search/docs MCP servers when installed and built-in web tools otherwise. Use when a question needs several external sources compared or synthesized, or a web task needs the user's logged-in browser. Not for a single quick lookup.

    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

896 bytes

6bbdd626d82d8b72…

.codex-plugin/plugin.json

plugin-manifest

2,695 bytes

8c560e66298034d0…

.cursor-plugin/plugin.json

file

563 bytes

1723dcd3ac49b7fd…

agents/analyze-dependencies.md

file

3,747 bytes

d046b11a37c33661…

agents/clarify-requirements.md

file

8,377 bytes

5badddbd5d913bcc…

agents/define-business-logic.md

file

6,066 bytes

2f9adc8e562b2efd…

agents/design-user-journey.md

file

6,896 bytes

8769633b922d0740…

agents/devils-advocate.md

file

13,295 bytes

a0d8fd33190719cb…

agents/fix-bugs.md

file

6,783 bytes

f2e115562c93cb9a…

agents/git-workflow.md

file

5,949 bytes

e7c510f8baa2b41c…

agents/implement-code.md

file

5,312 bytes

41a56888795650b4…

agents/plan-implementation.md

file

8,145 bytes

30237a615510856b…

agents/research-external.md

file

4,750 bytes

05f67c1e9aebbcdc…

agents/review-code.md

file

22,878 bytes

13a6e02d30c3c2c2…

agents/security-scan.md

file

7,643 bytes

bf9dbd26ea26f57c…

agents/sync-docs.md

file

4,848 bytes

0695927510d249e3…

agents/verify-code.md

file

5,488 bytes

df0c7e5131aa3a0f…

agents/write-tests.md

file

4,946 bytes

2af9cd3ba3bfceea…

assets/icon.png

asset

25,540 bytes

0854fd7ad8b11119…

hooks/auto-format.py

file

15,846 bytes

11a53d0baca4bfd7…

hooks/examples/child-git-guard.py

file

10,383 bytes

efaac793cceeba73…

hooks/examples/README.md

file

15,487 bytes

3c03173275408c21…

hooks/examples/verify-mutate-split.py

file

11,802 bytes

1c6ab640bec88d08…

hooks/hooks-codex.json

file

550 bytes

9eca13a24682436f…

hooks/hooks.json

file

1,552 bytes

d76af351f150c035…

hooks/protect-sensitive.py

file

15,690 bytes

caedafec98bcc64f…

hooks/session-start.py

file

22,438 bytes

df00b022ade42838…

hooks/stop-validator.py

file

35,898 bytes

a737cd7125a3c9d6…

hooks/utils.py

file

1,992 bytes

5b9ea7d852a5d7ce…

plugin.json

file

286 bytes

75994498fbbf98d0…

README.md

file

3,956 bytes

95113dbc421d9ac6…

skills/agent-creator/agents/openai.yaml

skill

315 bytes

164d73e6f4670859…

skills/agent-creator/SKILL.md

skill

2,690 bytes

31d813e6102cceeb…

skills/auto-dev/agents/openai.yaml

skill

274 bytes

52783692834fcfa4…

skills/auto-dev/SKILL.md

skill

17,385 bytes

b61a84d6bde2f79d…

skills/brainstorming/agents/openai.yaml

skill

410 bytes

9bf831e5cbca6d87…

skills/brainstorming/SKILL.md

skill

4,638 bytes

4ba90e1d00aa19ac…

skills/child-session/agents/openai.yaml

skill

423 bytes

98763169f46a6e05…

skills/child-session/SKILL.md

skill

7,232 bytes

a7285100977f9aae…

skills/code-intel/agents/openai.yaml

skill

385 bytes

60568864fff668da…

skills/code-intel/SKILL.md

skill

14,226 bytes

8d74ac401cfacc81…

skills/control-loop/agents/openai.yaml

skill

372 bytes

e175a02f30d2e8f3…

skills/control-loop/SKILL.md

skill

17,276 bytes

21a35ecb94ad80a8…

skills/cross-engine-review/agents/openai.yaml

skill

340 bytes

6337b0cb864c5869…

skills/cross-engine-review/README.md

skill

1,429 bytes

bc209b7aa59ac23c…

skills/cross-engine-review/SKILL.md

skill

13,900 bytes

64fdcc4b8d28ed3a…

skills/debug/agents/openai.yaml

skill

500 bytes

1bd4f906d59089fc…

skills/debug/references/hypothesis-evidence.md

skill

1,779 bytes

66a7444c4cf77e93…

skills/debug/SKILL.md

skill

5,548 bytes

a07a72808aeec5d4…

skills/harness-export/agents/openai.yaml

skill

491 bytes

d65659c68700517a…

skills/harness-export/SKILL.md

skill

13,022 bytes

628f231eb4766d82…

skills/multi-perspective-review/agents/openai.yaml

skill

313 bytes

c34cc1820b72d1e7…

skills/multi-perspective-review/conflict-resolution.md

skill

10,030 bytes

75f77481a6fc78dc…

skills/multi-perspective-review/deliberation-pattern.md

skill

14,866 bytes

dca213466072e790…

skills/multi-perspective-review/examples.md

skill

13,995 bytes

ecd635874d47c354…

skills/multi-perspective-review/perspectives-guide.md

skill

10,033 bytes

9380d0eb51762ddf…

skills/multi-perspective-review/SKILL.md

skill

10,663 bytes

cb00b6ab4b370590…

skills/plan-task/agents/openai.yaml

skill

286 bytes

bf5b3b3c8f7fd044…

skills/plan-task/references/boundary-check.md

skill

11,559 bytes

f747d5078f69bfa2…

skills/plan-task/references/elicitation.md

skill

8,618 bytes

0bbf224d30e432c4…

skills/plan-task/references/plan-format.md

skill

2,809 bytes

0b5ab4c4b870489f…

skills/plan-task/references/project-discovery.md

skill

1,029 bytes

0adf524fe98acb81…

skills/plan-task/references/task-tools-fallback.md

skill

9,618 bytes

f52950699e67a8d2…

skills/plan-task/SKILL.md

skill

9,096 bytes

bb3381c21f94a736…

skills/review/agents/openai.yaml

skill

409 bytes

90e58ed26131e098…

skills/review/references/engineering-evidence.md

skill

2,247 bytes

ea349e883d21da35…

skills/review/references/visual-qa.md

skill

1,296 bytes

7206c7c154d4eedb…

skills/review/SKILL.md

skill

14,000 bytes

04ec2233b729c4b5…

skills/session-history/agents/openai.yaml

skill

374 bytes

87035b58085c0f41…

skills/session-history/SKILL.md

skill

3,451 bytes

7669de74b13abab2…

skills/skill-forge/agents/openai.yaml

skill

408 bytes

44e07462980f2df8…

skills/skill-forge/SKILL.md

skill

5,253 bytes

9dd4b39b32f78818…

skills/test/agents/openai.yaml

skill

271 bytes

dcf9e7b05aabf888…

skills/test/SKILL.md

skill

4,241 bytes

66b5e092af071c3f…

skills/using-hiway-kit/agents/openai.yaml

skill

334 bytes

717d440f8db673a0…

skills/using-hiway-kit/SKILL.md

skill

893 bytes

c7c10118b9bb7cf6…

skills/web-research/agents/openai.yaml

skill

376 bytes

79b4edc6cdc8f3f4…

skills/web-research/references/source-evidence.md

skill

1,480 bytes

fefc4f7f6b879152…

skills/web-research/SKILL.md

skill

5,055 bytes

54a06437e59c2ca7…

hiway-kit — Frequently asked questions

What is hiway-kit?
hiway-kit is an AI plugin in the HOL registry. Discipline kit for coding agents with 17 skills for planning, automated implementation, testing, debugging, review and multi-session coordination, where work counts as done only when the project's own checks pass.
How do I install hiway-kit?
Install hiway-kit in your harness: Codex — codex plugin marketplace add This-HW/hiway-kit; Claude Code — /plugin marketplace add This-HW/hiway-kit; Cursor — npx [email protected] add This-HW/hiway-kit. Full step-by-step guidance is on the HOL plugin page.
How do I install hiway-kit in HOL Guard?
To install hiway-kit in HOL Guard, start with hol-guard plugin install this-hw/hiway-kit --apply. The complete step-by-step install guide for HOL Guard is on the HOL plugin page.
How do I install hiway-kit in Codex?
To install hiway-kit in Codex, start with codex plugin marketplace add This-HW/hiway-kit. The complete step-by-step install guide for Codex is on the HOL plugin page.
How do I install hiway-kit in Claude Code?
To install hiway-kit in Claude Code, start with /plugin marketplace add This-HW/hiway-kit. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
How is the Trust Score for hiway-kit computed?
hiway-kit has a HOL Trust Score of 74 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/this-hw%2Fhiway-kit/trust
Who publishes hiway-kit?
hiway-kit is published by This-HW 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