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 agentmods add commands/tornikegomareli/claude-plugin-codex/adversarial-reviewgit clone --depth 1 https://github.com/tornikegomareli/claude-plugin-codexWrote 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/tornikegomareli/claude-plugin-codex/adversarial-review)<a href="https://agentmods.dev/commands/tornikegomareli/claude-plugin-codex/adversarial-review"><img src="https://agentmods.dev/badge/commands/tornikegomareli/claude-plugin-codex/adversarial-review.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00485 |
| Opus 5 | $0.00016 | $0.00243 |
| Sonnet 5 | $0.00006 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00049 |
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 5d 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
Run an adversarial Claude Code review that questions the chosen implementation, design tradeoffs, and hidden assumptions.
Raw slash-command arguments:
$ARGUMENTS
Core constraint:
- This command is review-only.
- Do not fix issues, apply patches, or suggest that you are about to make changes.
- Your only job is to run the review and return Claude's output verbatim to the user.
Locating the companion script:
- The companion script is
scripts/claude-companion.mjsinside this plugin's root directory (the installedclaudeplugin directory that contains.codex-plugin/plugin.json). - Always invoke it with an absolute path.
Execution mode rules:
- If the raw arguments include
--wait, do not ask. Run in the foreground. - If the raw arguments include
--background, do not ask. Run with--background. - Otherwise, estimate review size the same way as
@claude review(git status and shortstat checks), recommend waiting only for clearly tiny changes, and ask the user exactly once, in plain conversation, with the recommended option first and marked "(Recommended)":- Wait for results
- Run in background
Argument handling:
- Preserve the user's arguments exactly, including any trailing focus text.
- The focus text steers the adversarial review; pass it through unchanged.
Foreground flow:
- Run:
node "<plugin-root>/scripts/claude-companion.mjs" adversarial-review "$ARGUMENTS"
- Return the command stdout verbatim, exactly as-is.
Background flow:
- Run the same command with
--backgroundappended. - After launching, tell the user: "Claude adversarial review started in the background. Check
@claude statusfor progress."
Sandbox requirements:
- The companion spawns the
claudeCLI, which needs network access to reach the Anthropic API. - If the sandbox blocks the command or Claude reports a connection error, rerun the same shell command with escalated permissions and explain why in the justification.
- Do not work around a sandbox denial by improvising your own review or edits; the command's value is Claude's independent output.
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.
- 5d ago First seen · 45 lines · 32 tokens per session scan A c7c11501bac4
adversarial-review is a command published in the GitHub repository tornikegomareli/claude-plugin-codex (9 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 485 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.