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 EzraApple/skills-init --skill adversarial-reviewgit clone --depth 1 https://github.com/EzraApple/skills-initWrote 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/ezraapple/skills-init/adversarial-review)<a href="https://agentmods.dev/skills/ezraapple/skills-init/adversarial-review"><img src="https://agentmods.dev/badge/skills/ezraapple/skills-init/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/ezraapple/skills-init/adversarial-review"><img src="https://agentmods.dev/badge/skills/ezraapple/skills-init/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 | $0.00041 | $0.00627 |
| Opus 5.5 | $0.00016 | $0.00251 |
| Sonnet 5.5 | $0.00008 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00063 |
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 18d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial review
Use fresh reviewer and validator subagents to find issues that survive an attempt to disprove them. A clean review is useful; finding volume is not a measure of quality. The parent agent coordinates, checks evidence, and synthesizes the result.
Review requests are read-only. Apply fixes only when the user's request also authorizes them. A writable checkout does not supply that authorization.
Establish the change
Resolve the requested files, diff, or plan and its intended behavior. Inspect the base and current revision, including local changes when relevant. If the revision changes during review, identify which conclusions need checking again.
Trace changed behavior through representative callers and state transitions. Look for violations of actual contracts: failure handling, ordering, permissions, compatibility, persistence, and recovery. A concern needs a reachable trigger and a consequence, not just an unfamiliar pattern.
Read only the relevant additional lens:
- For breakage beyond the diff, read change-impact.md.
- For caller-facing API or component design, read interfaces.md.
Review in fresh contexts
Start each reviewer in a fresh context window without inherited conversation history. Give reviewers the same concise packet: the user request, scope, constraints, base and current revisions, diff or plan, and paths to relevant project guidance. Add each reviewer's risk focus. Exclude the builder's reasoning, prior conclusions, and other reviewers' findings.
Choose distinct risk lanes from the changed surfaces and requested scrutiny, such as correctness, security, interfaces, or operations. Keep reviewers read-only and independent until their passes finish. Require a concrete failure path, location, evidence, and focused correction for each finding.
If fresh subagents are unavailable, disclose that limitation. Sequential passes in one context do not provide the same independence.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 18d ago Changed · -168 lines · -18 tokens per session d0a3ba96e5b9
- 2mo ago First seen · 234 lines · 59 tokens per session scan A a4fa46382607
adversarial-review is a skill published in the GitHub repository EzraApple/skills-init (2 stars, last pushed 19d ago), licensed MIT. It adds 41 tokens to every session and 627 once invoked, about $0.0002 per session on Opus 5.5. 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
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
design-review
Five-dimension design audit (frontend UI/UX · server data-model & flow · endpoint spec · daemon-runtime/SDK & local-cache-first · built-in skill/agent-role), executed by a NON-implementing agent. Every dimension gets a verdict; N/A only with a stated reason. A dimension the design silently skipped must be surfaced as…
codebase-design
Design maintainable module interfaces, review scoped code changes, and simplify implementations with behavioral verification. Use for code review, cleanup, testability, and module design work.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
tech-lead/code-review
A checklist-based method for examining code for correctness, security, performance, clarity, and ease of maintenance.
pr-blocker-summarizer
Summarizes open pull requests into a blockers-first standup digest. Activates when the user asks to summarize open PRs, find blocked pull requests, generate a PR standup, or triage review backlog from a PR export.