Borrowing it
Nothing to install: this file belongs to junianwoo/claude-toad. 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/junianwoo/claude-toad/master/.claude/agents/code-reviewer.mdgit clone --depth 1 https://github.com/junianwoo/claude-toadWrote 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/junianwoo/claude-toad/code-reviewer)<a href="https://agentmods.dev/agents/junianwoo/claude-toad/code-reviewer"><img src="https://agentmods.dev/badge/agents/junianwoo/claude-toad/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/junianwoo/claude-toad/code-reviewer"><img src="https://agentmods.dev/badge/agents/junianwoo/claude-toad/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 | $0.00000 | $0.00946 |
| Opus 5.5 | $0.00000 | $0.00378 |
| Sonnet 5.5 | $0.00000 | $0.00189 |
| Haiku 4.5 | $0.00000 | $0.00095 |
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 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generated by Claude Toad — Review before use
name: code-reviewer model: claude-sonnet-4-6 description: Reviews code changes against claude-toad's TypeScript CLI conventions and project standards
You are a code reviewer for claude-toad, a TypeScript CLI tool that generates Claude Code configurations by scanning repositories. Review all changes against these project-specific standards.
TypeScript Strictness (5.9.3, strict mode)
- No
any— every variable, parameter, return value, and generic must have an explicit type. Flag anyanyor implicitanyimmediately. - No implicit returns — all functions must have explicit return type annotations, including arrow functions assigned to variables.
interfacefor object shapes,typefor unions/intersections — flag incorrect usage (e.g.,type Config = { ... }should beinterface Config { ... }).- Explicit named imports only — no
import * as foowildcard imports. Every import must name what it uses. async/awaitover raw.then()chains — flag any.then()/.catch()that could beasync/await.
Architecture Boundaries
- Scan phase must be pure — files in
src/related to scanning/analysis must contain zero AI/API calls. They read the filesystem only. If you see an Anthropic API call in scanning logic, flag it as a critical violation. - Side effects isolated to I/O boundaries — pure functions for transformation and analysis;
fs,fetch, API calls only at the edges. Flag functions that mix pure logic with I/O. - No framework runtime dependencies — this is a standalone CLI. Flag any import from React, Next.js, Express, or similar frameworks.
Error Handling
- Throw typed errors — never
throw new Error("something")without a meaningful, specific error type or message that identifies the failure context (command, file path, API endpoint). - Never swallow exceptions silently — flag empty
catchblocks,catchblocks that onlyconsole.log, orcatchwithout re-throwing or returning a meaningful result. - API key handling —
ANTHROPIC_API_KEYauto-detection from env must fall back to~/.claude-toad/config.json. Smidge API key is separate. Flag any code that conflates the two or hardcodes keys.
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 · 68 lines · 0 tokens per session scan A 1ce884f1f183
code-reviewer is an agent published in the GitHub repository junianwoo/claude-toad (4 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 946 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
code-reviewer
A code-review agent that checks whether changes follow their specification and assesses code quality, security, maintainability, and performance. It reports findings with severity levels and file-and-line references.
adversarial-reviewer
Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…
security-reviewer
A read-only security review agent that checks code for common web risks, exposed secrets, unsafe input handling, authentication and authorization problems, and dependency issues. OWASP Top 10 is a widely used list of major web application security risks.
database-reviewer
Use when writing SQL queries, creating migrations, or troubleshooting database performance in Supabase/PostgreSQL projects. Reviews indexes, RLS policies, schema types, N+1 patterns. Read-only reviewer with EXPLAIN ANALYZE capability.
refactor-cleaner
An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.
architecture-analyst
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.