Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add GaosCode/PlanWeave --skill plan-auditorgit clone --depth 1 https://github.com/GaosCode/PlanWeaveWrote 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/gaoscode/planweave/plan-auditor)<a href="https://agentmods.dev/skills/gaoscode/planweave/plan-auditor"><img src="https://agentmods.dev/badge/skills/gaoscode/planweave/plan-auditor/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/gaoscode/planweave/plan-auditor"><img src="https://agentmods.dev/badge/skills/gaoscode/planweave/plan-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 51 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00059 | $0.02022 |
| Opus 5.5 | $0.00024 | $0.00809 |
| Sonnet 5.5 | $0.00012 | $0.00404 |
| Haiku 4.5 | $0.00006 | $0.00202 |
Grade A, and why
plan-auditor 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 1mo ago.
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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Auditor
Use this skill to audit an existing PlanWeave plan. The default output is findings and revision order; do not import a new plan, execute blocks, repair state, or rewrite the package while auditing.
Quick Start
- Find the authority sources: user request, PRD, schema, design docs, current code, and the PlanWeave package.
- Read
project-graph.jsonwhen present, every canvasmanifest.json, source prompts, task/block definitions, canvas structure, dependencies, validation output, andplanweave schemaoutput when available. - Before judging task completeness, identify the plan's main value flows or lifecycle flows and fill the required Flow Coverage table.
- Compare the plan against real goals, data-flow coverage, object lifecycles, contracts, execution order, prompts, failure paths, and verification criteria.
- Report a verdict first:
PASS,NEEDS_REVISION, orBLOCKED. - List findings by severity, with evidence and concrete plan changes.
Plan Update Boundary
- Audit findings name the needed task, block, edge, prompt, review, or validation update; they do not apply the change.
- If the user explicitly asks to apply revisions, finish the audit first, then use the Plan Package semantic editing boundary: resolve CLI workspace paths, edit only
project-graph.json, canvasmanifest.json, and source prompt Markdown needed for the revision, and run canvas-scoped plus project validation. - Do not edit runtime
state.json,results/, active canvas selection, recovery transactions, or implementation artifacts from this skill.
Required Output
- Verdict:
PASS,NEEDS_REVISION, orBLOCKED. - Flow Coverage table before findings.
- Findings by severity.
- Recommended revision order.
Flow Coverage table:
| Flow | Trigger/Input | Core Processing | External Dependency | State/Storage | Interface/Consumer | Output/Side Effect | Failure Path | Verification | Gaps |
|---|
For every cell, cite exact PlanWeave task/block ids, prompts, reference files, and validation methods when they exist. Use Gap: for missing task coverage, prompt coverage, dependency edge, verification, real behavior, or required failure handling.
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.
- 1mo ago First seen · 129 lines · 59 tokens per session scan A 9f0cc561a9c1
plan-auditor is a skill published in the GitHub repository GaosCode/PlanWeave (424 stars, last pushed 5d ago), licensed MIT. It adds 59 tokens to every session and 2,022 once invoked, about $0.0002 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"…
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…
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…
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…