Agent Skills › withkynam/vibecode-pro-max-kit › vc-audit-vc

vc-audit-vc

GitHub

用于验证Agent Harness层内部一致性，检查Claude与Codex代理对等性、技能注册表同步、README.md及协议文件连接。当代理、技能或配置文件发生变动时触发审计。

.claude/skills/vc-audit-vc/SKILL.md withkynam/vibecode-pro-max-kit

触发场景

代理、技能或配置文件发生变动需要验证Agent Harness层内部一致性检查Claude/Codex代理对等性

安装

npx skills add withkynam/vibecode-pro-max-kit --skill vc-audit-vc -g -y

更多选项

非标准路径

npx skills add https://github.com/withkynam/vibecode-pro-max-kit/tree/main/.claude/skills/vc-audit-vc -g -y

不安装直接使用

npx skills use withkynam/vibecode-pro-max-kit@vc-audit-vc

指定 Agent (Claude Code)

npx skills add withkynam/vibecode-pro-max-kit --skill vc-audit-vc -a claude-code -g -y

安装 repo 全部 skill

npx skills add withkynam/vibecode-pro-max-kit --all -g -y

预览 repo 内 skill

npx skills add withkynam/vibecode-pro-max-kit --list

SKILL.md

Frontmatter

{
    "name": "vc-audit-vc",
    "layer": "contract",
    "description": "Audit agent harness health: Claude\/Codex agent parity, skill registry consistency, README.md sync, and protocol file wiring. Use when agents, skills, README.md, or development-protocol files move, split, or drift.",
    "trigger_keywords": "harness audit, agent parity, skill audit, guide sync"
}

Audit VC (Version Control Harness Health)

Output style: Follow process/development-protocols/communication-standards.md — answer-first, plain language, no unexplained jargon, TL;DR on long responses.

Use this skill to verify that the agent harness layer is internally consistent and correctly wired across Claude, Codex, README.md, and protocol files.

For context routing, grouping, and discoverability audits, use the audit-context skill instead.

Workflow

Run the Claude/Codex agent parity validator:

node .claude/skills/vc-audit-vc/scripts/validate-agent-parity.mjs

Run the shared skill discovery validator:

node .claude/skills/vc-audit-vc/scripts/validate-skills.mjs

Run the README.md sync validator:

node .claude/skills/vc-audit-vc/scripts/validate-guide-sync.mjs

Run the protocol wiring validator:

node .claude/skills/vc-audit-vc/scripts/validate-protocol-wiring.mjs

Run the seed/scaffold consistency validator:

node .claude/skills/vc-audit-vc/scripts/validate-seeds.mjs

Run the kit portability validator:

node .claude/skills/vc-audit-vc/scripts/validate-kit-portability.mjs

Run the skill invocation wiring validator:

node .claude/skills/vc-audit-vc/scripts/validate-skill-invocation-wiring.mjs

Run the agent frontmatter validator:

node .claude/skills/vc-audit-vc/scripts/validate-agent-frontmatter.mjs

If any script reports failures, inspect the referenced files and patch the smallest relevant surface.
Re-run the failed validators until they pass.

Rules

Treat .claude/agents/ as canonical for agent definitions; .codex/agents/ mirrors them.
Treat .claude/skills/ as canonical for skills; .agents/skills/ is the Codex discovery symlink.
When updating agents, mirror Claude markdown and Codex TOML surfaces together.
Treat process/_seeds/ as an optional legacy scaffold surface in the live repo. Its absence is a warning-only audit result unless the user is explicitly auditing export-kit scaffolding.
Treat validator warnings as audit findings unless the user asks for a strict cleanup.
For context routing and discoverability audits, delegate to audit-context.