Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/paultyng/skill-issuenpx agentmods add skills/paultyng/skill-issue/review-planWrote 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/paultyng/skill-issue/review-plan)<a href="https://agentmods.dev/skills/paultyng/skill-issue/review-plan"><img src="https://agentmods.dev/badge/skills/paultyng/skill-issue/review-plan.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00111 | $0.02772 |
| Opus 5 | $0.00056 | $0.01386 |
| Sonnet 5 | $0.00022 | $0.00554 |
| Haiku 4.5 | $0.00011 | $0.00277 |
Grade A, and why
review-plan 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 8d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Review
Pre-flight review of an implementation plan markdown file. Produces a verdict (READY / NEEDS_REVISION / BLOCKED) and a prioritized findings table. Used standalone and as a pre-execution gate by implement-plan.
This is a document review, not a code review. No static analyzers. No diff scoping. The plan is treated as the artifact under test; the codebase is read-only context for feasibility checks.
Workflow
1. Resolve the plan file
Priority order:
- Explicit path from the invocation (e.g.
/review-plan .plans/auth-rewrite.md). ./.plans/PLAN.mdin the current working directory.- Latest by mtime in
./.plans/*.md(typicallyYYYY-MM-DD-<feature>.mdper convention). - Legacy fallback (one-release transition):
./PLAN.md, then latest by mtime in./docs/plans/*.md. If either resolves, warn once:Plan resolved from legacy path <X>; consider moving under .plans/.
If none resolve, stop and ask the user for a path. Do not guess.
CLAUDE.md override: if the project CLAUDE.md (or CLAUDE.local.md) contains a Plans live in <path> directive, use <path> as the primary discovery dir instead of .plans/.
2. Load context
- Read the resolved plan file fully.
- Read any docs the plan references inline (
./REVIEW.md,./CLAUDE.md, design docs cited). - For each file path mentioned in the plan, confirm the file exists (or is named as new in the plan). Missing files referenced as "edit" targets are a feasibility issue.
- If the plan references prior work in commits or PRs, capture branch + base ref for the run metadata header.
Do not read the entire codebase. Read only what the plan references plus enough to verify the named files exist.
3. Apply the plan-shape contract
The plan must satisfy these structural rules. Any violation contributes to NEEDS_REVISION or BLOCKED per the verdict rules.
Where a task states a requirement level, it SHOULD use RFC 2119 key words (MUST / SHOULD / MAY) so mandatory and optional steps are unambiguous (see the normative-language rule).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 217 lines · 111 tokens per session scan A 23692be7e9ad
review-plan is a skill published in the GitHub repository paultyng/skill-issue (9 stars, last pushed 27d ago), licensed MIT. It adds 111 tokens to every session and 2,772 once invoked, about $0.0006 per session on Opus 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 2026-08-31.
Other skills, from other repositories
skillnote
Self-hosted skill registry for OpenClaw. Stores procedures your team writes (name, description, body), syncs them to disk before each task, and collects which-helped/which-failed signals from the agent so the registry improves over time.
chatcrystal-debug-recall
Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
megalinter-check
Collect MegaLinter lint errors for the current repository. Use when the user wants to know if the code passes linting, why the MegaLinter CI job fails, or before/after fixing lint errors. Two modes - watch a CI job (GitHub Actions, GitLab CI, Azure Pipelines, Bitbucket Pipelines) and parse its logs, or run MegaLinter…
assistant
Assistant — on any repo, scan README→docs→AGENTS→CONTRIBUTING→PR templates→task runners→devcontainer→CI→configs before code; cite sources; prefer AGENTS.md for agent behavior; portable across Cursor/Copilot/Claude; use agent-toolkit CLI when needed.
design-improvement
WHAT - Browser-grounded iterative design improvement. Consumes design-assessment findings, defines direction, prioritizes safe vs ambiguous changes, implements within existing design system, runs app, captures rendered evidence via browser, reviews and iterates. Reuses evidence model — no new scoring framework.