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/nikuscs/codex-cc-pluginnpx agentmods add skills/nikuscs/codex-cc-plugin/claude-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/nikuscs/codex-cc-plugin/claude-adversarial-review)<a href="https://agentmods.dev/skills/nikuscs/codex-cc-plugin/claude-adversarial-review"><img src="https://agentmods.dev/badge/skills/nikuscs/codex-cc-plugin/claude-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/nikuscs/codex-cc-plugin/claude-adversarial-review"><img src="https://agentmods.dev/badge/skills/nikuscs/codex-cc-plugin/claude-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 | $0.00027 | $0.00094 |
| Opus 5.5 | $0.00011 | $0.00038 |
| Sonnet 5.5 | $0.00005 | $0.00019 |
| Haiku 4.5 | $0.00003 | $0.00009 |
Grade A, and why
claude-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 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.
What it actually says
Claude Adversarial Review
Run the structured adversarial review flow.
This path accepts extra focus text and uses the adversarial review prompt template.
node plugins/claude/scripts/claude-companion.mjs adversarial-review --scope auto "Challenge the design tradeoffs."
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 · 15 lines · 27 tokens per session scan A 2d7f53b064ae
claude-adversarial-review is a skill published in the GitHub repository nikuscs/codex-cc-plugin (6 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 94 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
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
triage
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
writing-extensions
Guide for authoring a new in-process MCP tool extension for gerrit-mcp-server. Use when a user wants to add new Gerrit tools, port a standalone plugin MCP server into the extension framework, or needs a worked example of the ExtensionContext API.
gerrit-task-query
Use when asked to check, list, or act on tasks for a Gerrit change. Triggers on phrases like "what tasks are blocking", "which tasks are actionable", "check task status", "what do I need to do for this change", "what is blocking this change".
gerrit-workflow
This skill should be used when the user asks to "submit a change to Gerrit", "push for review", "upload a patch", "update a change in Gerrit", "add a patch set", "work with Gerrit", "push to refs/for", "fix a missing Change-Id", "amend a Gerrit change", or any task involving git operations in a repository hosted on…