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/yunsii/wezdecknpx agentmods add skills/yunsii/wezdeck/adversarial-reviewWrote 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/yunsii/wezdeck/adversarial-review)<a href="https://agentmods.dev/skills/yunsii/wezdeck/adversarial-review"><img src="https://agentmods.dev/badge/skills/yunsii/wezdeck/adversarial-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/yunsii/wezdeck/adversarial-review"><img src="https://agentmods.dev/badge/skills/yunsii/wezdeck/adversarial-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 | $0.00085 | $0.02614 |
| Opus 5.5 | $0.00034 | $0.01046 |
| Sonnet 5.5 | $0.00017 | $0.00523 |
| Haiku 4.5 | $0.00009 | $0.00261 |
Grade A, and why
adversarial-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 11d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial review (platform skill — single source)
Who runs: the coding agent (OpenClaw Main / Claude-TUI / Codex-TUI), not the human.
Never tell the user to copy-paste run.sh as the primary path.
Never replace this with a solo monologue and call it 对抗审查 (that is 设计批判).
This directory is the only skill + runner unit. Other paths are symlinks (user-level or in-repo discovery). Do not maintain a second SKILL.md body.
Who runs what
| Actor | Duty |
|---|---|
| Human | Intent only:「对抗审查」「审一下这批改动」「按推荐审查」 |
| Any agent | Load this skill → resolve TOOL + TARGET → run → disclose |
| Host headless backends | claude / codex / grok as find/refute (not ACP by default) |
When to load / run
- User asks for 对抗审查 / adversarial review / multi-role review
- Write-task checklist: acceptance suggests review
- Runtime code/scripts changed (any git TARGET the agent may review)
- After editing this toolkit itself →
dogfood
Skip / redirect:
- Pure docs/tests-only (runner auto-skips); user explicitly skips with reason
- Design docs / RFC / ADR / 方案提案 (no runtime diff): do not force this
skill. Use 设计评审 (structured checklist in host
validation.md→ Design proposal review) or brainstorm only when the user still wants alternative approaches. Never label a doc critique 对抗审查.
Multi-role minimum
| Role | Stance | Runner stage |
|---|---|---|
| find / reviewer | guilty-until-proven | stage 1 |
| refute / refuter | kill weak findings | stage 2 |
| repro | empirical in sandbox | stage 3 |
- Prefer different families than the writer (strategy B via
--writer). - Same capability twice OK → label SINGLE-MODEL / degraded; do not skip refute.
- Solo essay without opposite roles → 设计批判, not 对抗审查.
Paths: TOOL vs TARGET (critical)
Do not assume ./skills/adversarial-review exists in the repo under review.
| Name | Meaning |
|---|---|
| TOOL_HOME | This skill/runner directory (where run.sh lives) |
| TARGET | Git repo being reviewed (--repo or current git toplevel) |
What ships with it
20 files 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.
- lib/context-pack.sh 21 KB runs code
- lib/findings-schema.json 1.4 KB
- lib/impact/extract-symbols.sh 2.0 KB runs code
- lib/impact/impact.sh 5.1 KB runs code
- lib/impact/resolvers/grep.sh 2.6 KB runs code
- lib/impact/test-impact.sh 2.4 KB runs code
- lib/impact/test-pack-slice.sh 4.2 KB runs code
- lib/provider.sh 7.5 KB runs code
- lib/providers/claude.sh 1.1 KB runs code
- lib/providers/codex.sh 2.5 KB runs code
- lib/providers/grok.sh 1009 B runs code
- lib/roles-lib.sh 672 B runs code
- lib/roles.conf 1.2 KB
- lib/rubric-lib.sh 849 B runs code
- lib/rubric.conf 1.3 KB
- lib/select-backends.sh 5.2 KB runs code
- prompts/critic.md 2.6 KB
- prompts/refute.md 1020 B
- prompts/repro.md 1.1 KB
- run.sh 27 KB runs code
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.
- 11d ago Changed f1c82846501f
- 1mo ago Changed c1c0f028f902
- 1mo ago First seen · 225 lines · 85 tokens per session scan A 332810f06317
adversarial-review is a skill published in the GitHub repository yunsii/wezdeck (4 stars, last pushed 5d ago), licensed MIT. It adds 85 tokens to every session and 2,614 once invoked, about $0.0003 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
code-reviewer
A code-reviewing role that checks code for bugs, security weaknesses, readability problems, design issues, and performance concerns.
Systematic debugging
Use when you hit a bug, test failure, or unexpected behavior — find the root cause before changing code.
defect-hunting
Use when reviewing code, auditing an app, writing a guard rule or test, or certifying any threshold/constant/formula. Finds the defects a diff review structurally cannot see — the second write path, the mis-calibrated constant, the rule that cannot fail. Triggers from code-reviewer, /app-audit, qa-engineer…
hyperframes-quality
Review and gate an editable HyperFrames composition or its rendered video before delivery. Use after building, revising, diagnosing, or rendering a HyperFrames project when layout, contrast, deterministic timing, transitions, animation choreography, rendered-frame fidelity, or high-quality acceptance needs…
fitness-functions
Use when designing architectural fitness functions as GC rules — periodic checks that verify system-wide properties like layer boundaries, coupling trends, and complexity hotspots, complementing per-change constraints with weekly architectural health monitoring.
gitnexus-impact-analysis
Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: "Is it safe to change X?", "What depends on this?", "What will break?".