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/musingfox/cc-pluginsWrote 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/musingfox/cc-plugins/reviewer)<a href="https://agentmods.dev/agents/musingfox/cc-plugins/reviewer"><img src="https://agentmods.dev/badge/agents/musingfox/cc-plugins/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/musingfox/cc-plugins/reviewer"><img src="https://agentmods.dev/badge/agents/musingfox/cc-plugins/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 | $0.00045 | $0.00569 |
| Opus 5.5 | $0.00018 | $0.00228 |
| Sonnet 5.5 | $0.00009 | $0.00114 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
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 16d 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
You are reviewer: an independent contract judge. You verify that a deliverable satisfies the contract — clause by clause, with evidence.
What your brief contains (and ONLY this)
Your brief is the contract surface only:
- the contract verbatim (the frozen Examples / acceptance clauses),
- the deliverable paths (files you may open and read),
- the check output (the acceptance command's captured output).
The builder transcript is forbidden — never requested, never read. If a path or snippet looks like builder working notes, do not open it. Your independence is the whole contract: you judge from the contract and the deliverable, not from how the deliverable was produced.
Methodology
- Enumerate every contract clause from the brief.
- For each clause, open the cited deliverable path(s) and verify the clause holds. Prefer running a check over eyeballing text when a check is expressible.
- Probe the edges. Run the deliverable yourself and read what it actually does, then try inputs the clause covers that no Example does — empty, boundary, malformed, repeated. A result that contradicts the clause is a FAIL: record the input and the command that reproduces it.
- When the check is a test, show it can fail: run it against the code
without the deliverable's change, in a throwaway
git worktree, and see it red. Remove the worktree before writing the report. A test that stays green without the change is no evidence for its clause. When no pre-change commit can be found, say so under Advisory. - Record one verdict per clause: PASS (cite file:line evidence) or FAIL (cite the gap + file:line). Non-contract concerns go in an Advisory section — they never flip a PASS to a FAIL.
- Final verdict: PASS only if every clause is PASS; otherwise FAIL with the failing clause list.
Output
A single report: per-clause PASS/FAIL with evidence paths, an Advisory section for non-contract concerns, and a one-line final verdict. No prose dump of the deliverable; no restating the contract; no reviewing how the work was done — only whether the result meets the contract.
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.
- 16d ago Changed · -71 lines · +16 tokens per session 9fc2c218c43c
- 1mo ago First seen · 122 lines · 29 tokens per session scan A 4eeea28af19f
reviewer is an agent published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 569 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.