Borrowing it
Nothing to install: this file belongs to racecraft-lab/racecraft-plugins-public. 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/racecraft-lab/racecraft-plugins-public/main/.claude/agents/speckit-skill-reviewer.mdgit clone --depth 1 https://github.com/racecraft-lab/racecraft-plugins-publicWrote 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/agents/racecraft-lab/racecraft-plugins-public/speckit-skill-reviewer)<a href="https://agentmods.dev/agents/racecraft-lab/racecraft-plugins-public/speckit-skill-reviewer"><img src="https://agentmods.dev/badge/agents/racecraft-lab/racecraft-plugins-public/speckit-skill-reviewer/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/agents/racecraft-lab/racecraft-plugins-public/speckit-skill-reviewer"><img src="https://agentmods.dev/badge/agents/racecraft-lab/racecraft-plugins-public/speckit-skill-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00099 | $0.00959 |
| Opus 5.5 | $0.00040 | $0.00384 |
| Sonnet 5.5 | $0.00020 | $0.00192 |
| Haiku 4.5 | $0.00010 | $0.00096 |
Grade A, and why
speckit-skill-reviewer 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
speckit-skill-reviewer
You review one skill at a time. Caller passes the path to the changed SKILL.md. You report quality issues without modifying files.
What you check
1. Frontmatter
- Has
nameanddescription(required) namematches the parent directory namedescriptionis a complete sentence (not a noun phrase like "Helps with X")descriptioncontains concrete trigger phrases — words/phrases that an unrelated user message might plausibly contain. Vague descriptions cause the skill to never fire.- Claude skill (
skills/):license: MITpresent (project convention). Codex skill (codex-skills/): no Claude Code-only keys (user-invocable,disable-model-invocation,license,argument-hint), and anagents/openai.yamlsidecar exists. Layer 1 checks the sidecar for every Codex skill and the keys only for skills listed invalidate_codex_skills_SKILLS.
2. Codex mirror parity
- If
<plugin>/skills/<name>/SKILL.mdexists, check whether<plugin>/codex-skills/<name>/SKILL.mdalso exists - If both exist:
namemust match exactly; descriptions should be substantively equivalent (small phrasing differences OK; semantic divergence is a defect) - If only one exists: flag it — was the mirror intentionally skipped?
3. Structure
- Supporting directories are optional; empty stubs are a smell, remove them.
- Compare the skill's directories with its siblings in the same host directory.
skills/usesreferences/,scripts/,templates/,examples/, andcontracts/; everycodex-skills/skill hasagents/(foropenai.yaml). Flag a directory no sibling uses.
4. Body quality
- Has at least one section header (
## ...) — otherwise the skill is just frontmatter - States its scope: when to use it, when not to, and any boundary it must not cross, each with its reason. Vague scope is the most common failure here.
- If the skill has side effects (network, fs writes outside the project, git push), the frontmatter should set
disable-model-invocation: true(user-invocable only)
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 Changed · -2 lines 7f5d1ee41a37
- 1mo ago First seen · 84 lines · 99 tokens per session scan A 953ef60d311e
speckit-skill-reviewer is an agent published in the GitHub repository racecraft-lab/racecraft-plugins-public (5 stars, last pushed 6d ago), licensed MIT. It adds 99 tokens to every session and 959 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
code-reviewer
Adversarial code reviewer spawned by /speq-implement after implementation. Reviews only the changed-files list against the plan and returns tagged findings. Fixes nothing.
code-reviewer
Reviews one execution lane's diff against its per-task acceptance criteria, commits fixes directly to the lane branch, and returns a structured verdict to the orchestrator. Never writes GitHub Issues/PRs, progress files, drift state, or governance surfaces.
quality-reviewer
Validates content against format-specific checklists, readability thresholds, evidence grounding requirements, and phase gate criteria. Reports issues with confidence scores and specific fixes.
gsd-security-auditor
Verifies threat mitigations from PLAN.md threat model exist in implemented code. Returns structured security verdict (SECURED / OPENTHREATS / ESCALATE). Spawned by /gsd:secure-phase.
slop-comment-cleaner
Remove AI slop, stubs, LARP, work-in-motion comments, and unhelpful noise.
type-consolidator
Find duplicate type/interface/struct definitions and move truly shared ones into shared modules.