vc-audit-vc
vc-audit-vc checks that your agent harness layer stays internally consistent and correctly wired across Claude, Codex, documentation, and protocol files. Run validators to catch agent definition drift, skill discovery mismatches, guide sync failures, and wiring breaks—then patch and re-run until all checks pass.
vc-audit-vc validates agent harness consistency across Claude, Codex, README, and protocol files.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-06-21
vc-audit-vc validates agent harness consistency across Claude, Codex, README, and protocol files. vc-audit-vc checks that your agent harness layer stays internally consistent and correctly wired across Claude, Codex, documentation, and protocol files. Run validators to catch agent definition drift, skill discovery mismatches, guide sync failures, and wiring breaks—then patch and re-run until all checks pass.
Use it when
- vc-audit-vc compares Claude and Codex agent definitions against the skill registry to ensure both agents expose the same skills.
- Yes.
Verify before relying
Read SKILL.md below before installing (12 files). Open directory: indexed for reading, not audited.
Install
withkynam/vibecode-pro-max-kit/vc-audit-vc · repository language: JavaScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What does vc-audit-vc audit agent harness health for?
vc-audit-vc checks that your agent harness layer stays internally consistent and correctly wired across Claude, Codex, documentation, and protocol files. It validates agent definitions, skill registry alignment, README sync, and protocol file wiring to catch drift and mismatches before they break agent behavior.
How does vc-audit-vc validate Claude and Codex agent parity?
vc-audit-vc compares Claude and Codex agent definitions against the skill registry to ensure both agents expose the same skills, frontmatter, and invocation wiring. It flags parity gaps so you can align agent behavior across both implementations.
Can vc-audit-vc verify README.md and protocol files are in sync?
Yes. vc-audit-vc validates that README.md, protocol files, and agent definitions reference the same skills, versions, and wiring patterns. It detects when guides drift from actual agent code and alerts you to re-sync them.
What happens when vc-audit-vc detects agent skill discovery issues?
vc-audit-vc checks skill invocation wiring and agent frontmatter correctness to ensure skills are discoverable and callable. When it finds wiring breaks or missing frontmatter, it diagnoses the drift so you can patch agent definitions and re-run validation until all checks pass.
How does vc-audit-vc handle agent and skill file moves or splits?
vc-audit-vc detects and diagnoses drift when agents, skills, or files move or split by cross-referencing harness layer wiring, registry entries, and protocol definitions. It helps you identify broken paths and misaligned references after refactoring.
Is vc-audit-vc open source and what license does it use?
Yes, vc-audit-vc is released under the MIT license, making it free to use, modify, and distribute in both open and closed projects.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
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:
bash node .claude/skills/vc-audit-vc/scripts/validate-agent-parity.mjs - Run the shared skill discovery validator:
bash node .claude/skills/vc-audit-vc/scripts/validate-skills.mjs - Run the README.md sync validator: ```bash node
(truncated - see the full file via the links below)
File tree — 12 files
.claude/skills/vc-audit-vc/SKILL.md
.claude/skills/vc-audit-vc/scripts/export-benchmark-kit.mjs
.claude/skills/vc-audit-vc/scripts/fixtures/validate-skill-invocation-wiring/fail.md
.claude/skills/vc-audit-vc/scripts/fixtures/validate-skill-invocation-wiring/pass.md
.claude/skills/vc-audit-vc/scripts/validate-agent-frontmatter.mjs
.claude/skills/vc-audit-vc/scripts/validate-agent-parity.mjs
.claude/skills/vc-audit-vc/scripts/validate-guide-sync.mjs
.claude/skills/vc-audit-vc/scripts/validate-kit-portability.mjs
.claude/skills/vc-audit-vc/scripts/validate-protocol-wiring.mjs
.claude/skills/vc-audit-vc/scripts/validate-seeds.mjs
.claude/skills/vc-audit-vc/scripts/validate-skill-invocation-wiring.mjs
.claude/skills/vc-audit-vc/scripts/validate-skills.mjs
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Audit agent harness layer for internal consistency and wiring correctness”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
vc-audit-context validates your project's context layer, routing tables, and shared-skill discovery across agents. Run built-in validators to catch missing context files, broken skill references, and protocol misalignment, then regenerate your machine-readable skill catalog.
vc-generate-context creates and updates process/context/all-context.md, your project's durable knowledge layer for sharing context across agents. It supports full scans for new projects, delta updates for existing repos, and grouped context generation for organized documentation. Validation scripts ensure routing integrity before context is marked refreshed.
This skill guides you through complete internationalization setup and auditing for modern web applications. Configure your chosen i18n framework, systematically replace user-facing strings with localization keys, ensure consistent coverage across target locales (en-US and zh-CN by default), and validate pluralization and formatting rules. The workflow covers framework selection, locale file organization, error message localization, and testing strategies.
i18n-expert guides you through complete internationalization setup and auditing for React, Next.js, and Vue codebases. It handles framework selection, locale file organization, string replacement with translation keys, and validation of locale parity across your target languages. The skill ensures proper error localization, metadata translation, and language switching with persistence.
vc-autopilot is a contract skill that owns the provisional goal block artifact for Autopilot Mode. It emits the structured 9-field block after clarification, detects resume scenarios from pasted blocks, and validates artifacts against the D1 spec. The skill also handles V7 UPDATE variants when validation completes.
vc-audit-plans scans your active plan inventory to flag stale, completed, or obsolete artifacts and recommend archival or cleanup actions. It validates plan status against your codebase, detects misplaced task artifacts, and surfaces a summary table with classifications and next steps. Use it for periodic maintenance, post-burst reconciliation, or when plan cleanup has drifted.
More skills helmor-bump-vendors (Apache-2.0)