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 ChianW/C31 --skill c31-reviewgit clone --depth 1 https://github.com/ChianW/C31Wrote 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/chianw/c31/c31-review)<a href="https://agentmods.dev/skills/chianw/c31/c31-review"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-review/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/chianw/c31/c31-review"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-review.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 | $0.00032 | $0.04155 |
| Opus 5.5 | $0.00013 | $0.01662 |
| Sonnet 5.5 | $0.00006 | $0.00831 |
| Haiku 4.5 | $0.00003 | $0.00415 |
Grade A, and why
C31-review 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 — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multilingual Triggers
| Language | Trigger phrases |
|---|---|
| EN | review, 审查, code review, verify, 验证, verify-work |
| ZH | 审查, 代码审查, 验证 |
| JA | レビュー, コードレビュー, 検証 |
Output language: Respond automatically in the user's conversation language.
C31 Review
Reviews code changes using dynamically selected reviewer personas, then runs a
verify-work pass: UAT walkthrough, verifier validation, and decision coverage
logging. Writes memory/.planning/phases/XX-VERIFICATION.md.
When to Use
- Before creating a PR or merging code
- After completing a coding or implementation task
- When the user says "code review", "审查", "review my code", "看看这段代码", "verify", "验证", "verify-work", or "review"
Modes
| Mode | Trigger | Behavior |
|---|---|---|
| interactive (default) | No mode token | Review, UAT, ask user how to proceed |
| autofix | mode:autofix |
Apply safe_auto fixes, auto-run UAT, report residuals |
| report-only | mode:report-only |
Read-only review + UAT, no edits |
| headless | mode:headless |
Programmatic mode; structured output, no interaction |
Conflicting mode flags: stop and emit Review failed. Reason: conflicting mode flags.
Severity Scale
All reviewers use P0-P3:
| Level | Meaning | Action |
|---|---|---|
| P0 | Critical: vulnerability, data loss, logic breakage | Must fix before merge |
| P1 | High: likely hit in normal usage, breaking contract | Should fix |
| P2 | Moderate: edge case, perf regression, maintainability | Fix if straightforward |
| P3 | Low: minor improvement, narrow scope | User's discretion |
Action Routing
autofix_class |
Default Owner | Meaning |
|---|---|---|
safe_auto |
review-fixer |
Local, deterministic fix — can auto-apply |
gated_auto |
downstream-resolver |
Concrete fix exists but changes behavior/contracts |
manual |
downstream-resolver |
Actionable work requiring handoff |
advisory |
human |
Report-only (learnings, rollout notes, residual risk) |
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.
- 1mo ago First seen · 379 lines · 32 tokens per session scan A e2528f0f2a23
C31-review is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 4,155 once invoked, about $0.0001 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 skills, from other repositories
agent-production-validator
Agent skill for production-validator - invoke with $agent-production-validator.
agent-tester
Agent skill for tester - invoke with $agent-tester.
score-harness
5-dimension scorecard (0-100, grade A/B/C/F) for a scaffolded harness. Dimensions: Repo understanding (25%), Agent usefulness (25%), MCP safety (20%), Test coverage (15%), Publish readiness (15%). Emits a 6-field badges block (score + mcpRisk + 4 booleans) ready for the harness README. Exit 0 A/B, 1 C, 2 F.
validate-harness
Release-readiness umbrella check for a scaffolded harness — runs doctor, witness verify, hardcoded-path scan, MCP server config, and GCP Secret Manager validation in one shot. Exits non-zero if any sub-check fails.
frontend-manual-testing
Use when the task changes anything a user sees in a web app - booting it, driving flows with the browser tools, the four-width check, console/network/keyboard checks and the visual checklist.
acceptance-criteria-gwt
Use when writing acceptance criteria for a task - express each as an observable Given/When/Then that QA can execute, including negative cases.