Borrowing it
Nothing to install: this file belongs to khaoss85/agent-crm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/khaoss85/agent-crm/main/.agents/skills/adversarial-review/SKILL.mdgit clone --depth 1 https://github.com/khaoss85/agent-crmWrote 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/khaoss85/agent-crm/adversarial-review)<a href="https://agentmods.dev/skills/khaoss85/agent-crm/adversarial-review"><img src="https://agentmods.dev/badge/skills/khaoss85/agent-crm/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/khaoss85/agent-crm/adversarial-review"><img src="https://agentmods.dev/badge/skills/khaoss85/agent-crm/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 | $0.00094 | $0.01542 |
| Opus 5 | $0.00047 | $0.00771 |
| Sonnet 5 | $0.00019 | $0.00308 |
| Haiku 4.5 | $0.00009 | $0.00154 |
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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orient yourself first
npm run crm -- app inspect --json
Read valid, then problems[], then limitations[], in that order. Every problem is fixed or reported before anything is built on top of it, and every limitation is a hard boundary on what you may claim. Then read packages[], capabilities[], resources[], actions[], policies[] and providers[]: that list is what exists. A capability absent from the report does not exist, whatever a record name, a label or a document suggests.
If the repository documents this skill names are absent, you are in a project built from this framework rather than in the framework itself. The inspection report is then the source of truth and those documents are optional background — do not guess at their contents, and do not assume a path exists because this skill names it.
The contract you review against
This skill reviews a pull request against this repository's own contract, so it needs that repository. Read AGENTS.md, docs/QUALITY_GATES.md, the PR's ExecPlan under docs/plans/, the ADRs it touches, and the JTBD rows it claims. Those four are the contract you are reviewing against — the PR body is a claim, not evidence.
Where one of those documents is genuinely absent, review against the inspection report's problems[] and limitations[] and the project's own tests, and say in the report which contract you could not read. A review that invents the standard it reviewed against is not a review.
1. Verify live state before reading code
Never trust the task description's summary of the PR. Establish, from the API and from git:
- head SHA and commit count; base is the latest main (
git merge-baseequals the base SHA); - every check green, zero unresolved review threads, no conflicts;
- the diff is this milestone only — list any file that is not, and justify or flag it;
- nothing tracked that must never be:
.env, databases, logs, build output, browser profiles, webhook captures, signed artifacts, generated starter output,node_modules; - the specific fixes the description claims are actually present in the diff.
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.
- 10d ago First seen · 87 lines · 94 tokens per session scan A 5e177cc5e0a6
adversarial-review is a skill published in the GitHub repository khaoss85/agent-crm (2 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 1,542 once invoked, about $0.0005 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 skills, from other repositories
critique-theater
Five-dimension design quality review — score the artifact against craft, brand, accessibility, and copy, then fix what falls short before handing it over.
code-refiner
Deep code simplification and refactoring preserving behavior across Python, Go, TypeScript, Rust. Targets complexity, anti-patterns, readability debt. Triggers on: "simplify this code", "refactor for clarity", "reduce complexity", "make this more readable", "tech debt cleanup", "too much nesting".
package-optimizer
Evaluate one existing package or bounded package family from recorded evaluator evidence and a capability profile, then propose retain, simplify, strengthen, retire, or inconclusive without editing. Use when optimizing a skill, agent, hook, rule, command, utility, or preset; evaluating whether package detail is…
beautify-with-pingfusi
Beautify or redesign an existing website through iterative pingfusi review rounds with a real human reviewer. Use when asked to "beautify this website," "make this page look professional," "polish this UI/design," "improve the visual design," or finish an AI-built page when there is no reference site to match. Do not…
plan-review
Pre-implementation plan audit stress-testing scope, assumptions, risks, and failure modes before code is written. Triggers on: "review this plan", "is this plan solid", "what am I missing", "challenge my assumptions", "stress-test this", "/plan-review".
fix-with-pingfusi
Fix or polish an existing website clone/draft using pingfusi review rounds. Use when the user says "fix it with pingfusi", "polish this clone", "make this match the original", or asks to finish/verify a draft built by any tool (ditto, lovable, v0, hand-written) until the review passes.