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-review-adversarialgit 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-adversarial)<a href="https://agentmods.dev/skills/chianw/c31/c31-review-adversarial"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-review-adversarial/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-adversarial"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-review-adversarial.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 | $0.00000 | $0.00436 |
| Opus 5 | $0.00000 | $0.00218 |
| Sonnet 5 | $0.00000 | $0.00087 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
C31-review-adversarial 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 12d 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.
What it actually says
Multilingual Triggers
| Language | Trigger phrases |
|---|---|
| EN | C31-review-adversarial |
| ZH | 对抗审查 |
| JA | 対抗レビュー |
Output language: Respond automatically in the user's conversation language.
C31-review-adversarial
Purpose
Adversarial reviewer — cross-component failure scenarios, stress-test unstated assumptions, construct edge cases.
Severity Calibration
| Level | Meaning | Fix Timeline |
|---|---|---|
| P0 | Critical — single failure cascades, data loss on edge case, security breach | Block merge |
| P1 | High — retry storm, thundering herd, partial state corruption | Fix in PR |
| P2 | Medium — graceful degradation gaps, missing circuit breaker | Fix this sprint |
| P3 | Low — additional monitoring/alerting needed | Backlog |
Review Checklist
- Failure Propagation — Does a downstream failure kill the caller? Retry loops exponential?
- Unstated Assumptions — What does code assume about inputs? Network? State? Test those.
- Edge Cases — Empty collections? Max int? Null/undefined? Timezone boundary? Leap second?
- Concurrent Access — Race conditions? Double-submit? TOCTOU vulnerabilities?
- Resource Exhaustion — What happens at memory limit? Disk full? Connection pool drained?
- Bad Input — Fuzz-test surfaces: oversized payloads, malformed JSON, injection attempts
- Dependency Failure — What if DB/redis/third-party is slow or returns garbage?
- State Machine Gaps — Are there transition paths not handled? Invalid states reachable?
Output Format
For each issue: P[0-3] | <attack-vector> | <one-line summary> | <file:line>
Last line: RESILIENCE_SCORE: [0-10] — 10 = no attack surface found, 0 = trivial cascade failure.
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.
- 12d ago First seen · 41 lines · 0 tokens per session scan A 3088abbdb793
C31-review-adversarial is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 436 tokens. 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-code-review-swarm
Agent skill for code-review-swarm - invoke with $agent-code-review-swarm.
agent-swarm-pr
Agent skill for swarm-pr - invoke with $agent-swarm-pr.
agent-reviewer
Agent skill for reviewer - invoke with $agent-reviewer.
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
agent-pr-manager
Agent skill for pr-manager - invoke with $agent-pr-manager.
agent-analyze-code-quality
Agent skill for analyze-code-quality - invoke with $agent-analyze-code-quality.