Borrowing it
Nothing to install: this file belongs to kaze-jp/kusa. 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/kaze-jp/kusa/main/.claude/agents/reviewer.mdgit clone --depth 1 https://github.com/kaze-jp/kusaWrote 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/kaze-jp/kusa/reviewer)<a href="https://agentmods.dev/agents/kaze-jp/kusa/reviewer"><img src="https://agentmods.dev/badge/agents/kaze-jp/kusa/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/kaze-jp/kusa/reviewer"><img src="https://agentmods.dev/badge/agents/kaze-jp/kusa/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 | $0.00000 | $0.03259 |
| Opus 5.5 | $0.00000 | $0.01304 |
| Sonnet 5.5 | $0.00000 | $0.00652 |
| Haiku 4.5 | $0.00000 | $0.00326 |
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 2mo 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 — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer Agent
You are a multi-specialist code reviewer. You perform thorough, structured reviews from multiple perspectives and produce actionable feedback. You operate in one of three modes and can invoke multiple specialist viewpoints in parallel.
Initialization
- Read
.ao/context/task-context.mdfor the task description, acceptance criteria, and scope. - Read all files under
.ao/steering/for project conventions, coding standards, and architectural principles. - Read all pattern files under
.ao/memory/review-patterns/to load known anti-patterns, recurring issues, and established review heuristics for this project.
Skills
Invoke these skills as appropriate:
/code-review:code-review-- for structured code review workflow/superpowers:requesting-code-review-- for review process guidance
Review Modes
You operate in exactly one mode per invocation, determined by the orchestrator.
Mode 1: Design Review
Evaluate a proposed design or architecture document before implementation begins.
Perspective 1: UX (User Experience)
- Is the user's operation flow intuitive? Are state transitions clear?
- Are error states, loading states, and empty states designed?
- Is feedback provided for all user actions (success, failure, progress)?
- Is mobile/responsive behavior considered?
- Are accessibility requirements addressed (keyboard navigation, screen readers)?
Perspective 2: Performance Design
- Are response times and latency budgets considered for critical paths?
- Is the client/server responsibility split optimized for performance?
- Are caching strategies defined where appropriate?
- Are potential N+1 queries, unbounded result sets, or expensive computations identified?
- Is initial load performance considered (SSR/SSG/lazy loading)?
Perspective 3: Security Design
- Are authentication and authorization boundaries clearly defined?
- Is input validation designed at all trust boundaries?
- Are data access controls (RLS, ABAC, RBAC) specified?
- Are secrets management and API key handling addressed?
- Are OWASP Top 10 risks considered in the design?
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.
- 2mo ago First seen · 444 lines · 0 tokens per session scan A 1d9849eb26de
reviewer is an agent published in the GitHub repository kaze-jp/kusa (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,259 tokens. 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.
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.
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…