adversarial-review
Skill0 starsChanged 2 months agoMITView on GitHub
Use when reviewing a PR, patch, or design. Attack the change as a skeptic: enumerate failure modes, missing tests, unsafe defaults, and privilege edges before approving or merging.
109 other projects use a version of this.
Adopted by
Most recently taken up by
- anton-abyzov/specwithcodetheir own version, first seen Nov 16, 2026
- Axect/skillstheir own version, first seen Nov 16, 2026
- magnusrodseth/dotfilestheir own version, first seen Nov 16, 2026
- lennoxsaint/Skillstheir own version, first seen Nov 15, 2026
- fabioc-aloha/Alex_ACT_ONEtheir own version, first seen Nov 15, 2026
- samuelralak/How-I-Worktheir own version, first seen Nov 15, 2026
Used with
Projects with it also use rethink, root-cause-analysis and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
fabioespindulaSkillrethink
Reframe a plan, idea, or decision before the user commits to it. Use when the user asks to rethink, step back, pressure-test, gut-check, decide, right-size, simplify, think bigger about, or evaluate a concrete plan or decision in product, strategy, technical architecture, career, life, company direction, or personal priorities. This skill improves decision quality before action: clarify the real question, challenge assumptions, compare alternatives, calibrate ambition, classify the operating mode, surface risks, and recommend a next move. Do not use for broad future exploration without a concrete decision; that belongs to a think-big or research-style skill.
Also in 3 projects that use this
MicrosoftSkillroot-cause-analysis
Use when a Regional Retail Manager asks I'm seeing unusual inventory movement at our Northwest stores. Can you help me understand what's happening?
Also in 3 projects that use this
anasahmed07Skillbetter-auth-best-practices
Skill for integrating Better Auth - the comprehensive TypeScript authentication framework.
Also in 4 projects that use this
DockerSkillfix-issue
Fix a single GitHub issue end-to-end: triage, research, write the fix, review, and create a PR. Use when asked to fix an issue: "fix issue 1234", "resolve #500", "create a PR for issue 200".
Also in 3 projects that use this
MicrosoftSkillpull-request
Write concise, focused pull request descriptions for Wassette — at most three sentences on the what and why, with an explicit note on any breaking public-API change and how users adapt. Use when opening or editing a Wassette pull request.
Also in 3 projects that use this
juriwiensSkillcodex-review
Run code review via Codex CLI
Also in 3 projects that use this
- +2 more from microsoft
Other versions109 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 109
- PrefectHQ/fastmcp★ 29ksame name
- jlowin/fastmcp★ 29ksame name
- mengxi-ream/read-frog★ 10ksame name
- epicenter-md/epicenter★ 4.8ksame name
- EpicenterHQ/epicenter★ 4.8ksame name
- basicmachines-co/basic-memory★ 4.6ksame name
- DanMcInerney/architect-loop★ 626same name
- deadlock-mod-manager/deadlock-mod-manager★ 584same name
- boraoztunc/skills★ 473same name
- syahiidkamil/Software-Engineer-AI-Agent-Atlas★ 404same name
99 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- api-compatSkill
- flaky-test-triageSkill
- incident-hotfixSkill
- perf-measure-firstSkill
- repro-firstSkill
- secrets-hygieneSkill
- skill-authorSkill
- test-plan-firstSkill
- yagni-sliceSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 98 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 15
Before merging high-risk changes (auth, payments, data deletion, public APIs).
- Distinctive: line 27
Do not merge, push to protected branches, or dismiss required reviews without authorization.
- Distinctive: line 28
Do not exfiltrate secrets found in the diff.
- Distinctive: line 34
Check tests for gaps relative to those failure modes.
“Common” is measured: kept by at least 6 in 10 of the 98 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Adversarial Review
When to use
- Reviewing a pull request, patch diff, or proposed design.
- The user asks for a "critical review", "threat model pass", or "what could go wrong".
- Before merging high-risk changes (auth, payments, data deletion, public APIs).
When not to use
- Rubber-stamping typo/docs-only PRs where risk is negligible.
- Pairing sessions where the goal is collaborative drafting, not gatekeeping (switch to review mode when ready).
- Replacing formal security audit/penetration test engagements.
Assumptions
- Access to the full diff, linked issue, and ability to run or reason about tests.
- Product/security context may be incomplete — call out assumptions explicitly.
- Do not merge, push to protected branches, or dismiss required reviews without authorization.
- Do not exfiltrate secrets found in the diff; follow secrets-hygiene instead.
Workflow
- Restate the change's purpose and trust boundaries in your own words.
- Hunt for failure modes: nulls, races, authz gaps, injection, unsafe defaults, partial failure.
- Check tests for gaps relative to those failure modes.
- File concrete, severity-tagged findings (blocker / should-fix / nit).
- Approve only when blockers are addressed or explicitly accepted by the owner.
Steps
- Intent check — Does the diff match the claimed purpose? Flag unrelated churn.
- Abuse cases — For each new input/surface: unauthenticated access, confused deputy, oversized payloads, replay, TOCTOU, and error-path leaks.
- Defaults & footguns — Fail-open vs fail-closed; permissive CORS; debug flags; default passwords; broad IAM.
- Data & teardown — Migrations, deletes, and retries: idempotency, backup/rollback, PII exposure in logs.
- Test gaps — Map each serious risk to a missing test; demand or add coverage for blockers.
- Report — Structured findings with file/line references and a clear merge recommendation.
Success criteria
- Review names specific failure modes, not only style nits.
- Missing tests for high-severity risks are called out.
- Unsafe defaults and authz edges are explicitly assessed.
- Findings are prioritized (blocker vs non-blocking).
- No unauthorized merge or secret leakage occurred during review.
Out of scope
- Full formal threat modeling workshops for an entire product.
- Legal/compliance sign-off.
- Rewriting the feature for the author unless asked.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

