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 maxedapps/agent-skills --skill code-reviewgit clone --depth 1 https://github.com/maxedapps/agent-skillsWrote 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/maxedapps/agent-skills/code-review)<a href="https://agentmods.dev/skills/maxedapps/agent-skills/code-review"><img src="https://agentmods.dev/badge/skills/maxedapps/agent-skills/code-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/maxedapps/agent-skills/code-review"><img src="https://agentmods.dev/badge/skills/maxedapps/agent-skills/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00063 | $0.00567 |
| Opus 5.5 | $0.00025 | $0.00227 |
| Sonnet 5.5 | $0.00013 | $0.00113 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
code-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 1mo 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Stance
- Review only what was asked. If the scope is unclear, ask.
- Look hard, report little. Try to break the code with realistic inputs, states, and sequences. Challenge the work, not its author.
- "Nothing worth changing" is a valid result. A short review is a good review.
- Don't edit code unless asked.
What counts as a finding
Report something only if all of these hold:
- There is a concrete way it fails or causes harm.
- That can realistically happen.
- The impact on users, data, security, or maintenance is real.
- Fixing it removes more risk or complexity than the fix adds.
Never report niche edge cases, hypothetical scale, style preferences, duplication that hurts nothing, the number of helpers or files, or ideas for making things "more flexible".
Where to look
Check what applies to the change:
- Correctness: wrong assumptions, error handling, races and async order, state and cleanup, and refactors that lost behavior.
- Security: authentication and authorization, injection, trusting client input, and secrets or personal data in code, logs, or URLs.
- Libraries: check behavior against the installed version's types and docs, not memory.
- Tests: do they protect behavior that matters? Flag missing coverage of real behavior, assertions on implementation details, excessive mocking, and tests that pass without proving anything. Don't ask for tests for their own sake.
- Data and APIs: breaking changes, migrations, and retries of side effects that aren't safe to repeat.
- UI: when practical, exercise the changed screens in a real browser with agent-browser.
- Complexity: unnecessary layers and wrappers, one-use helpers, speculative options or generic APIs, and defensive code for cases that can't happen. Prefer, in order: delete, use directly, local helper, shared abstraction, new abstraction.
- Plan and ADR: if the change implements a plan, report plan tasks that are missing or unverified, and conflicts with an accepted ADR.
What ships with it
3 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.
- 1mo ago Changed · -40 lines · -1 tokens per session 0a589e5bc0ec
- 1mo ago Changed e84c1633e5dc
- 1mo ago Changed · +1 lines 9e23e3166e2f
- 2mo ago First seen · 86 lines · 64 tokens per session scan A e67cbb613489
code-review is a skill published in the GitHub repository maxedapps/agent-skills (60 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 567 once invoked, about $0.0003 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 2026-08-30.
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…
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…
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…