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-multi-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-multi-review)<a href="https://agentmods.dev/skills/chianw/c31/c31-multi-review"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-multi-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-multi-review"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-multi-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 | $0.00034 | $0.01482 |
| Opus 5 | $0.00017 | $0.00741 |
| Sonnet 5 | $0.00007 | $0.00296 |
| Haiku 4.5 | $0.00003 | $0.00148 |
Grade A, and why
C31-multi-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 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multilingual Triggers
| Language | Trigger phrases |
|---|---|
| EN | multi-review, 代码审查, 检查这个, review |
| ZH | 多角色审查, 对抗审查 |
| JA | 多エージェントレビュー, 対抗レビュー |
Output language: Respond automatically in the user's conversation language.
C31-multi-review — 4-Agent Adversarial Review
Trigger
- User says: "review", "审查", "multi-review", "代码审查", "检查这个"
- C31-lfg Gate 5 auto-call (strict mode)
- PR submit pre-check (C31-git-worktree integration)
Input
- Target: file path, diff, or document to review
- Optional:
--strict(Gate 5 mode, fail on any blocker)
Workflow
Phase 1: Scope & Target Read
- Read the target file(s) or diff.
- If diff not provided and in git repo:
git diff HEAD. - Produce target digest (≤500 lines of relevant code + file list).
Phase 2: Spawn 4 Review Agents (Parallel)
Use sessions_spawn to dispatch 4 subagents simultaneously. Each receives:
- Full target digest
- Its persona prompt (below)
- Strict rule: find ≥1 real issue or exit (no hard-fabricated issues)
- Output schema (JSON)
{
"agent": "correctness",
"issues": [
{
"id": "C-01",
"severity": "blocker|warning|nit",
"line": 42,
"file": "src/foo.ts",
"description": "...",
"suggestion": "..."
}
]
}
Agents:
| Agent | Focus | Exit if Empty |
|---|---|---|
| Correctness | Logic errors, boundary conditions, error paths, type safety | Yes |
| Security | Injection risks, permission checks, sensitive data, dependency vulns | Yes |
| Maintainability | Readability, naming, complexity, docs, test coverage | Yes |
| Simplicity | Over-engineering, simpler alternatives, YAGNI violations | Yes |
Each agent is isolated — no shared context, no knowledge of other agents' findings.
Phase 3: Conflict Detection
After all 4 agents return, spawn Conflict Agent (1 subagent):
Task: Compare the 4 issue lists and flag contradictions:
- Correctness says "add mutex" vs Simplicity says "remove mutex, unnecessary"
- Security says "sanitize all inputs" vs Maintainability says "too many guards, refactor instead"
- Severity disagreements on same line (blocker vs nit)
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 · 166 lines · 34 tokens per session scan A 2a04bc1d9b3d
C31-multi-review is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 13d ago), licensed MIT. It adds 34 tokens to every session and 1,482 once invoked, about $0.0002 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
compare-harnesses
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.
diag-harness
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.
oia-manifest
Emit .harness/oia-manifest.json declaring layer alignment with the OIA v0.1 9-layer reference architecture. Self-describes the harness's MCP wiring, witness signing, audit log, identity posture (always 'none' at v0.1). --check verifies an existing manifest, --dry-run prints without writing, --json emits to stdout.
create-harness
Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a…
example-harness
Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/ example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot, OpenCode, GitHub Actions) + 10 vertical pods (devops, research, trading, support, legal, coding, education, sales, gaming…
repo-genome
7-section readiness scorecard for a LOCAL repo. Reports repo type + agent topology + MCP risk + test confidence + release readiness + recommended harness plan + scorecard. Exit 0 ready, 1 needs-work, 2 blocked. --json for the 6-field scorecard, --bundle for the ADR-031 schema-1 envelope.