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.
git clone --depth 1 https://github.com/Kenmege/codex-claude-companionWrote 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/commands/kenmege/codex-claude-companion/adversarial-review)<a href="https://agentmods.dev/commands/kenmege/codex-claude-companion/adversarial-review"><img src="https://agentmods.dev/badge/commands/kenmege/codex-claude-companion/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/commands/kenmege/codex-claude-companion/adversarial-review"><img src="https://agentmods.dev/badge/commands/kenmege/codex-claude-companion/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 | $0.00012 | $0.00356 |
| Opus 5 | $0.00006 | $0.00178 |
| Sonnet 5 | $0.00002 | $0.00071 |
| Haiku 4.5 | $0.00001 | $0.00036 |
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 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
/claude-review:adversarial-review
Preflight
- Prefer the helper binary
codex-claudeif it is available on PATH. - If it is not available, tell the user to install the helper with
npm install -g codex-claude-companionafter npmjs publish, or from a cloned checkout withnpm install -g ..
Plan
Runs an agentic adversarial review pass. Claude (Opus alias default, xhigh effort) gets read-only Read/Glob/Grep/Bash/Task/WebFetch/WebSearch tools so it can verify call sites, downstream consumers, and test gaps before challenging the design. Returns the helper output without paraphrasing it.
Commands
Use the exact argument tail the user supplied after
/claude-review:adversarial-review.
- Preferred:
codex-claude adversarial-review <user-arguments>
Useful flags:
--legacyto disable agentic mode (structured-output only).--mcp-config,--max-budget-usd,--add-dir,--system-prompt-extrafor workspace-specific control.
Keep this command read-only. The agent is restricted to read-only tools.
Verification
If the helper exits non-zero, report that failure exactly and stop.
Summary
Return the helper stdout verbatim.
Next Steps
If the user wants a persistent record, suggest --background plus
/claude-review:status. If they want the most exhaustive lane, suggest
/claude-review:elite-review.
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 · 50 lines · 12 tokens per session scan A 874fe4f51e62
adversarial-review is a command published in the GitHub repository Kenmege/codex-claude-companion (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 12 tokens to every session and 356 once invoked, about $0.0001 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 commands, from other repositories
lint
Check the project for naming, security and best-practice issues.
pi-code-review
Adversarial code review via Codex — break confidence in changes, not validate them.
pi-askall
Ask both Codex and Gemini the same question — get three perspectives with Claude synthesis.
pi-fact-check
Fact-check content via Gemini search + Claude verification — cross-provider claim validation.
pi-ask-gemini
Ask Gemini a question — get Google's perspective alongside Claude's.
conventions-check
Check AGENTS.md, CLAUDE.md, and the projected agent artifacts (skills, subagents, commands) against the repo's conventions.