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 duyet/oma --skill code-reviewgit clone --depth 1 https://github.com/duyet/omaWrote 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/duyet/oma/code-review)<a href="https://agentmods.dev/skills/duyet/oma/code-review"><img src="https://agentmods.dev/badge/skills/duyet/oma/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/duyet/oma/code-review"><img src="https://agentmods.dev/badge/skills/duyet/oma/code-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 | $0.00085 | $0.01063 |
| Opus 5.5 | $0.00034 | $0.00425 |
| Sonnet 5.5 | $0.00017 | $0.00213 |
| Haiku 4.5 | $0.00009 | $0.00106 |
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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
code-review
A review answers one question: is this change correct, safe, and something the team can live with? Read before you judge — a diff in isolation lies. The bug is usually in what the diff doesn't show: the caller that still passes the old shape, the error path that's now unreachable, the invariant two files over.
Scope the review first
- Get the diff.
git diff main...HEAD(or the branch/commit the user named). For an uncommitted change,git diff/git diff --staged. - Read what it touches. For every changed function, read its callers and
the code it calls.
grepthe symbol across the repo. "Looks orthogonal" is how regressions ship. - Know the intent. What was this supposed to do — the issue, the PR body, the commit message? A change can be flawless code and still be the wrong change. Review against the goal, not just against the compiler.
What to look for, in priority order
Spend your attention where the damage is greatest.
- Correctness — Does it do what it claims? Off-by-one, inverted
conditions, wrong operator, missing
await, unhandlednull/undefined, the empty-list and single-element cases, integer overflow, timezone/Datemistakes. Trace one real input through the new path by hand. - Security — Untrusted input reaching a sink: SQL/command/template injection, path traversal, SSRF, deserialization. Missing authz on a new route. Secrets in code, logs, or errors. A dependency bump to an unvetted version. See the checklist below.
- Error handling — Failures that are swallowed, logged-and-ignored, or caught too broadly. Resources (connections, files, locks, timers) leaked on the error path. Partial writes that leave state inconsistent.
- Concurrency & data — Races, unawaited promises, shared mutable state, N+1 queries, unbounded loops/allocations on user-controlled size, missing pagination, a migration that locks a hot table.
- Tests — Is the new behavior actually tested? A test that can't fail when the logic breaks is theater. Check the edge cases the code added, not just the happy path.
- Maintainability — Naming that misleads, a 200-line function that should be 50, duplicated logic, a leaked abstraction, dead code the change orphaned. Real, but never rank it above a correctness or security finding.
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 · 82 lines · 85 tokens per session scan A 36d200cda85b
code-review is a skill published in the GitHub repository duyet/oma (10 stars, last pushed 9d ago), licensed Apache-2.0. It adds 85 tokens to every session and 1,063 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 2026-08-31.
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…