Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jscraik/Agent-Skillsnpx agentmods add skills/jscraik/agent-skills/autoreviewWrote 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/jscraik/agent-skills/autoreview)<a href="https://agentmods.dev/skills/jscraik/agent-skills/autoreview"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/autoreview/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/jscraik/agent-skills/autoreview"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/autoreview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Excessive Agency · line 120 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00046 | $0.05239 |
| Opus 5 | $0.00023 | $0.02619 |
| Sonnet 5 | $0.00009 | $0.01048 |
| Haiku 4.5 | $0.00005 | $0.00524 |
Grade A, and why
autoreview 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.
How it starts
The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto Review
Philosophy
Run the bundled structured review helper as a closeout check. This is code review, not Guardian auto_review approval routing.
Codex review is the default when no engine is set. It usually delivers the best review results and should remain the normal final closeout engine.
When To Use
- user asks for Codex review / Claude review / autoreview / second-model review
- after non-trivial code edits, before final/commit/ship
- reviewing a local branch or PR branch after fixes
- branch or PR-base review before push, PR update, merge-readiness discussion, or handoff
When Not To Use
- Pure validation-only test execution belongs to testing or the repo closeout workflow, not autoreview.
- CodeRabbit/GitHub review-thread mutation, resolving PR conversations, merging, branch cleanup, and CI triage belong to PR/GitHub/CircleCI lanes, not autoreview.
- Do not select autoreview just because the request contains the word "review" when the actual work is PR thread mutation, merge orchestration, dependency triage, or validation-only reporting.
Routing Boundaries
- Local dirty closeout: choose local mode only for unstaged, staged, or untracked work in the current checkout.
- Branch/PR-base review: choose branch mode with the PR base for committed branch work, PR updates, or "before I push the PR update"; name the base-ref freshness state before trusting the diff.
- Commit review: choose commit mode for already-committed changes, especially clean main after a pull or merge.
- Second-model review: treat "second-model review" as an advisory autoreview request; classify findings as accepted, rejected, or blocked after source verification.
- Review panel: use Codex/Claude panels only when explicitly requested or when risk justifies the extra spend.
- Negative route: for validation-only requests, say autoreview is not selected and route to the better owner workflow.
- Negative route: for CodeRabbit or GitHub review-thread triage, say autoreview is not selected and route to the better owner workflow.
What ships with it
11 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.
- agents/openai.yaml 459 B
- references/contract.yaml 3.8 KB
- references/discovery-interview.md 2.6 KB
- references/evals.yaml 24 KB
- references/evals/generated.review-target-selection.md 961 B
- references/review-fixtures/malicious-changed.js 304 B runs code
- references/task-profile.json 1.5 KB
- scripts/autoreview 53 KB
- scripts/test-review-harness 367 B
- scripts/test-review-harness.ps1 1.3 KB runs code
- scripts/test-review-harness.py 9.0 KB runs code
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 · 361 lines · 46 tokens per session scan A 9c65166b9c3e
autoreview is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 7d ago), licensed Apache-2.0. It adds 46 tokens to every session and 5,239 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 2026-09-03.
Other skills, from other repositories
prepare-pr
A pull-request preparation workflow for a software branch. A pull request is a request for teammates to review and merge a set of code changes.
refactoring
Safely refactor code while maintaining behavior. Use when improving code structure, reducing duplication, extracting functions, or modernizing legacy code.
cross-review
Cross-vendor code review — have a different vendor's model (DeepSeek/GLM/any OpenAI-compatible endpoint) review the current diff to catch bugs a same-vendor reviewer misses. Use after a phase is green and before commit/merge, or for a second opinion on a risky diff.
code-review
Automated code review for pull requests using specialized review patterns. Analyzes code for quality, security, performance, and best practices. Use when reviewing code changes, PRs, or doing code audits.
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now…
pr-review-expert
Review GitHub PRs or GitLab MRs for correctness, security, compatibility, and affected test coverage, with actionable evidence tied to the diff.