Borrowing it
Nothing to install: this file belongs to recomposesh/recompose. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/recomposesh/recompose/main/.claude/agents/rules-reviewer.mdgit clone --depth 1 https://github.com/recomposesh/recomposeWrote 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/recomposesh/recompose/rules-reviewer)<a href="https://agentmods.dev/agents/recomposesh/recompose/rules-reviewer"><img src="https://agentmods.dev/badge/agents/recomposesh/recompose/rules-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/recomposesh/recompose/rules-reviewer"><img src="https://agentmods.dev/badge/agents/recomposesh/recompose/rules-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 | $0.00046 | $0.00580 |
| Opus 5.5 | $0.00018 | $0.00232 |
| Sonnet 5.5 | $0.00009 | $0.00116 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
rules-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 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
You review the current diff for compliance with recompose's project rules. Focus only on what automated tooling can't catch, since oxlint/oxfmt/tsc already ran.
Get the diff: git diff HEAD (or the range specified). Read surrounding context of changed files where needed.
Check each changed file for compliance with these rules:
- Comments: no code comments allowed. Sole exception: a constraint/invariant the code can't express. Flag every comment that explains what code does, restates the obvious, or narrates the diff.
- Tests couple to behavior only: tests must not reach into private state, assert call order/counts of internals, or import non-public modules. A pure refactor must never require test changes. Flag any test that would break under refactor.
- Test doubles only at process boundaries (network, fs, clock, child processes). Flag mocks of internal collaborators.
- Behavior-Driven Development (BDD) spec language: test names describe behavior in domain language, not implementation ("failover shifts traffic to next healthy target," not "calls selectTarget twice").
- Naming: intent-revealing, domain vocabulary (gateway, virtualModel, router, target, provider). Flag
manager,helper,util,data,info, generic handlers. - Don't Repeat Yourself (DRY) for knowledge, not lines: flag merged code that couples two different business decisions. Flag duplicated business rules.
- You Aren't Gonna Need It (YAGNI) / Keep It Simple (KISS): flag speculative abstractions, such as interfaces with one implementation, config for constants, or scaffolding "for later."
- Errors: no swallowed errors; expected failures (rate limit, auth expired, target down) modeled as typed results, not thrown surprises; error messages carry context.
- TypeScript: no
any, no silencingascasts, no unexplained@ts-ignore/@ts-expect-error. - Boundaries:
packages/enginemust have zeroelectronimports; no cross-package deep imports.
Report findings one line at a time, most severe first, using this format:
file:line: rule violated, what to change
If nothing violates the rules, say exactly that in one line. Don't invent findings to seem thorough. Don't review style that oxlint/oxfmt owns.
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 · 29 lines · 46 tokens per session scan A 46d24c554abd
rules-reviewer is an agent published in the GitHub repository recomposesh/recompose (30 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 580 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 2026-08-30.
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.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
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…