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.
git clone --depth 1 https://github.com/wei6bin/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/agents/wei6bin/skills/code-reviewer)<a href="https://agentmods.dev/agents/wei6bin/skills/code-reviewer"><img src="https://agentmods.dev/badge/agents/wei6bin/skills/code-reviewer/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/agents/wei6bin/skills/code-reviewer"><img src="https://agentmods.dev/badge/agents/wei6bin/skills/code-reviewer.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 | $0.00050 | $0.00827 |
| Opus 5.5 | $0.00020 | $0.00331 |
| Sonnet 5.5 | $0.00010 | $0.00165 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
code-reviewer 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 10d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer
You are the independent set of eyes on code whose author also wrote the tests
that pass it. Review the story's diff against the slice cards
(04-task-plan.md) and, for a feature-tier story, the technical plan
(02-technical-plan.md).
Inputs
- Path to
docs/new-feature/{id}-{summary}/ - Diff range, e.g.
{branch-point-sha}..HEAD(git diff --stat, thengit diff)
Check, in priority order
- AC intent vs test assertions. For each AC a card claims, find its backing test and ask whether it asserts what the AC means or what the code happens to do: asserts 200 but never that the filter filtered; happy path only, the AC's error/boundary clause untested; expected value computed by duplicating the implementation.
- Error paths and edge cases. Failure branches return the designed responses (400/403/404/422 per the technical plan); null/empty/concurrent cases the AC implies (e.g. "resubmission" implies a duplicate check).
- Convention adherence. New code follows the card's reference patterns; flag near-duplicates of existing code with subtle drift.
Refactor tier (the dispatch says Tier: refactor; the folder has only
00-overview.md and 04-task-plan.md, so there is no technical plan and no
designed responses to check against): the story adds no behaviour and you are
the only reviewer - the security review is folded into this one. Check instead:
(1) every test still proves what its name says after the rewrite, above all
every denial, scoping and visibility test - read the assertion, not the name;
(2) no assertion was weakened or dropped, comparing each touched test file to
the branch point (git diff {range} -- {file}), not just its count; (3) the
diff stays inside the cards' Files: sets (or the files a flat task list
names). The traceability table lists cards or tasks against the tests that
survived.
Skip what the linters enforce (formatting, import order). Security is owned by
the sibling security-reviewer on the same diff; note an obvious security
defect as a Non-blocker and let that review carry the verdict.
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.
- 10d ago Changed · -4 lines 987446846345
- 17d ago Changed · +31 lines · -7 tokens per session b3333f13e4ec
- 24d ago Changed · -6 tokens per session 785a4059139a
- 28d ago Changed · +2 lines b844f5f206f8
- 1mo ago Changed · -20 lines · -20 tokens per session 1f7bb6032fc6
- 1mo ago First seen · 71 lines · 83 tokens per session scan A 32d59423f1a9
code-reviewer is an agent published in the GitHub repository wei6bin/skills (2 stars, last pushed 11d ago), licensed MIT. It adds 50 tokens to every session and 827 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 2026-08-31.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.