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 joao-aires/agent-skills-public --skill reviewgit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/review)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/review"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/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/joao-aires/agent-skills-public/review"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/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 | $0.00045 | $0.00499 |
| Opus 5.5 | $0.00018 | $0.00200 |
| Sonnet 5.5 | $0.00009 | $0.00100 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
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 yesterday.
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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review
Read task guidance. Read deliver-reliable-changes for completion evidence and scope. Load the optional stack/domain guidance selected by task guidance only when relevant and available.
Establish and assess the review target
Pin target/base/head from the PR or current repository context; ask only if ambiguity changes the diff.
- Use the agreed request/spec/ticket when present, without requiring a tracker or inventing requirements.
- Follow the changed behavior from its caller to its result. Read enough surrounding code to understand existing callers, stored state and error handling, then check whether the new behavior agrees with them.
- Examine consequential assumptions: which actor is trusted, which changes happen together, what a retry means, and which consumers may still use the previous behavior. Use relevant specialists to deepen concerns that the diff actually changes.
- For affected UI use interface assessment expertise and interface-language expertise when installed; distinguish rendered/runtime evidence from static inspection.
- Use usability research expertise only for relevant supplied observations or a requested research plan, not to fabricate validation.
- Use code-review or security techniques only as supported by the client's invocation controls; review inline if delegation is unavailable.
Verify and report findings
Inspect existing checks and run appropriate authorized local tests when useful, including actual affected journeys. CI status alone does not establish that all tests passed.
For each finding, provide:
- Severity and concrete location/scenario.
- User or system impact.
- An actionable fix.
Support a defect with a concrete path through the changed code and the condition that makes it fail. Explain why the result violates an accepted requirement or existing behavior. When the concern depends on an assumption you could not verify, state that assumption and the evidence needed to resolve it. Distinguish missing evidence from a proven defect. Leave source unchanged by default, apart from owned test/runtime artifacts. Posting comments, applying fixes, approving or merging requires the request or trusted job policy. A changed head invalidates earlier review/test conclusions.
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.
- yesterday Changed · +19 lines 159e2884c907
- 2d ago Changed 50787b3b30b9
- 5d ago Changed 2cdb919d8bb5
- 7d ago First seen · 22 lines · 45 tokens per session scan A dec38cb707da
review is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 499 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 2026-10-15.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…