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 SerenecoTech/agent-skills --skill review-codegit clone --depth 1 https://github.com/SerenecoTech/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/serenecotech/agent-skills/review-code)<a href="https://agentmods.dev/skills/serenecotech/agent-skills/review-code"><img src="https://agentmods.dev/badge/skills/serenecotech/agent-skills/review-code/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/serenecotech/agent-skills/review-code"><img src="https://agentmods.dev/badge/skills/serenecotech/agent-skills/review-code.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 | $0.00105 | $0.00600 |
| Opus 5.5 | $0.00042 | $0.00240 |
| Sonnet 5.5 | $0.00021 | $0.00120 |
| Haiku 4.5 | $0.00011 | $0.00060 |
Grade A, and why
review-code 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.
What it actually says
Adversarial code review
A front door. All mechanics live in the engine — read
../../engine/ENGINE.md and follow it.
Resolve the target
Interpret the argument naturally, then hand the engine a target:
| Argument looks like | Target |
|---|---|
| nothing | uncommitted changes, untracked files included |
a branch name (git rev-parse resolves it) |
changes against that base |
| a commit SHA | the changes that commit introduced |
| a PR number or GitHub URL | verify with gh pr view <n> --json number, then review the checked-out branch |
| file paths that exist | those files |
If a token resolves to none of these, say so rather than guessing:
Could not resolve '<token>': not a file, directory, branch, commit SHA, or PR number.
For uncommitted targets, check git status first — if there is nothing, say so and stop.
Name the target in the brief, not in a flag. codex exec review refuses a target flag and
a prompt together, and the engine requires a per-round brief, so the target has to be described
in the brief itself — including that untracked files are in scope. invocation.md has the
measured command lines.
Then
- Load the engine and
rubric-code.md. Load other rubrics too if the change includes design or specification content — the door does not decide the evidence bar. - Follow the engine: loop shape, scope gate, rounds, convergence, output.
- Default to the verdict loop. Only enter the fix loop if the user explicitly authorised you to edit — "review my changes" does not.
Do not
- Paste diffs or file contents into the codex prompt. Codex reads the files itself; give it paths and a target description.
- Substitute your own review when codex is slow. That is what the user already had.
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 First seen · 53 lines · 105 tokens per session scan A 4547b35409b6
review-code is a skill published in the GitHub repository SerenecoTech/agent-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 600 once invoked, about $0.0004 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
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"…
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…
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…