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 tomzx/agents --skill adversarial-pr-reviewgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/adversarial-pr-review)<a href="https://agentmods.dev/skills/tomzx/agents/adversarial-pr-review"><img src="https://agentmods.dev/badge/skills/tomzx/agents/adversarial-pr-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/tomzx/agents/adversarial-pr-review"><img src="https://agentmods.dev/badge/skills/tomzx/agents/adversarial-pr-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 | $0.00132 | $0.05767 |
| Opus 5.5 | $0.00053 | $0.02307 |
| Sonnet 5.5 | $0.00026 | $0.01153 |
| Haiku 4.5 | $0.00013 | $0.00577 |
Grade C, and why
adversarial-pr-review scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/adversarial-pr-review-$PR_NUMBER Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(gh:*, ghx:*, git:*, uv:*, python:*, python3:*, node:*, npm:*, npx:*, go:*, cargo:*, make:*, docker:*, curl:*, ~/.agents/scripts/get-env:*, ~/.agents/scripts/should-post-to-github:*, ~/.agents/scripts/ How it starts
The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial PR Review
Answers the adversarial question: "what is the most likely way this change breaks, and can I make it break?" It assumes the change is broken and works to prove it, instead of checking that it does what it claims.
It complements the other review steps and does not replace them:
| Skill | Question | Evidence ceiling |
|---|---|---|
/review-pr |
Is the code well built? | L2 - Ruled out (static) |
/verify-pr |
Does the accepted behavior work? | L4 - Reproduced |
/validate-pr |
Is this the right product? | L2 - Ruled out (static plus issue reading) |
/adversarial-pr-review |
Which plausible failure happens, and can I reproduce it? | L4 - Reproduced |
Its contribution is adversarial reproduction: a ranked list of failure scenarios where the decisive ones were actually executed against the PR's code. A suspicion that was never tried is reported as unproven, never as a failure.
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md(PR Review Reports for report location and posting rules). - Apply the shared evidence standard in
../sdlc/references/evidence.md: label every finding with anL<n> - <Name>level. Abreaksverdict requires at least one decisive scenario atL3 - ExecutedorL4 - Reproduced. - If no argument is provided, target the pull request from
$PR_NUMBER(and$REPO). ghCLI authenticated with read access to the target repository.git worktreeavailable, and a toolchain able to run the PR's code (or the willingness to reportunprovenwhen it cannot).- A scratch directory outside the repository, by default
/tmp/adversarial-pr-review-$PR_NUMBER. - Read-only toward the PR and its repository: probes run against the worktree, write only under the scratch directory, and never modify, stage, or commit anything in the worktree.
- Self-contained evidence: the attack needs only the diff, the codebase, the PR description, and the linked issue. It never reads or waits for sibling reports (
assess-pr-risk,summarize-behavior-changes,analyze-test-coverage,validate-pr,verify-pr,review-pr). - Orchestrators (
review-pr-full,review-requested-prs) dispatch this skill concurrently with the analyze-test-coverage -> validate -> verify -> review chain and provideWORKTREE_DIR; because it shares no evidence with the chain, the parallel dispatch never weakens it.
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.
- today First seen · 405 lines · 132 tokens per session scan C 0df4078200d3
adversarial-pr-review is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 132 tokens to every session and 5,767 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-29.
Other skills, from other repositories
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.