Borrowing it
Nothing to install: this file belongs to xiaolai/vmark. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/xiaolai/vmark/main/.claude/skills/plan-audit/SKILL.mdgit clone --depth 1 https://github.com/xiaolai/vmarkWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xiaolai/vmark/plan-audit)<a href="https://agentmods.dev/skills/xiaolai/vmark/plan-audit"><img src="https://agentmods.dev/badge/skills/xiaolai/vmark/plan-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xiaolai/vmark/plan-audit"><img src="https://agentmods.dev/badge/skills/xiaolai/vmark/plan-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00069 | $0.00795 |
| Opus 5.5 | $0.00028 | $0.00318 |
| Sonnet 5.5 | $0.00014 | $0.00159 |
| Haiku 4.5 | $0.00007 | $0.00080 |
Grade A, and why
plan-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Audit
Overview
Two modes over the same plan. Audit (default) inspects completed work against the plan (WIs + acceptance + tests) and reports gaps, logic errors, and missing coverage with file/line references; it runs nothing. Verify runs the gates and marks every acceptance criterion; use it when asked to verify or confirm completion.
Workflow (Audit)
-
Locate the plan
dev-docs/plans/<plan>.md(local) or.claude/tdd-guardian/<plan>.md(tracked).- If unclear, ask for the plan path or the WI list.
-
Extract audit checklist
- For each WI, list:
- Goal
- Acceptance criteria
- Tests required
- Touched areas (files/symbols)
- For each WI, list:
-
Map implementation to WIs
- Use
git log,git show --stat,rg, and file inspection. - Record which files/commits satisfy each WI.
- Use
-
Gap & correctness analysis
- Check each acceptance item vs actual behavior.
- Find logic errors, edge-case failures, and incomplete flows.
- Validate test coverage against the “Tests (first)” section.
- If the plan references specs, verify implementation matches those specs.
- If the plan is missing acceptance/tests, record it as a plan-quality gap.
-
Report findings
- Order by severity: Critical → High → Medium → Low.
- Each finding must include:
- WI reference
- File path + line
- Why it violates the plan
- Expected behavior per plan
Output Format (required)
- Findings (ordered by severity)
File:lineand WI reference- Impact and suggested fix
- Plan Gaps Summary
- WI‑### → missing/partial acceptance items
- Test Coverage Gaps
- Missing tests, broken tests, or “test not written”
- Notes / Risks
- Any assumptions or unverified areas
- Evidence
- Cite concrete evidence for each finding (files/lines/commit IDs).
Audit Rules
- In audit mode, do not run tests unless the user explicitly asks; it is an inspection pass.
- Be strict about spec drift: if behavior diverges from plan text, flag it.
- If you cannot locate the plan, stop and ask for it.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · +16 lines · +27 tokens per session b54200cc2a00
- 2mo ago First seen · 63 lines · 42 tokens per session scan A a13695e438e2
plan-audit is a skill published in the GitHub repository xiaolai/vmark (878 stars, last pushed yesterday), licensed ISC. It adds 69 tokens to every session and 795 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…