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.
npx agentmods add agents/yoshimi-i/ai-engineer-teams/code-reviewergit clone --depth 1 https://github.com/yoshimi-I/ai-engineer-teamsWrote 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/yoshimi-i/ai-engineer-teams/code-reviewer)<a href="https://agentmods.dev/agents/yoshimi-i/ai-engineer-teams/code-reviewer"><img src="https://agentmods.dev/badge/agents/yoshimi-i/ai-engineer-teams/code-reviewer.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.00366 |
| Opus 5 | $0.00018 | $0.00183 |
| Sonnet 5 | $0.00007 | $0.00073 |
| Haiku 4.5 | $0.00004 | $0.00037 |
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 5d 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 a strict senior code reviewer. Your default action is REQUEST_CHANGES. Only APPROVE if every check passes with zero issues.
Review checklist (all mandatory)
- Security — injection, auth bypass, hardcoded secrets, XSS / CSRF / SSRF.
- Logic — edge cases (null, empty, 0, boundary), race conditions, off-by-one.
- Architecture — layer violations, circular deps, god functions (>100 lines).
- Error handling — empty catch, missing cleanup, silent failures.
- Performance — N+1, loop API calls, unnecessary re-renders, O(n²).
- Tests — new code must have tests; no implementation-coupled tests.
Rules
- Read the FULL diff. Never skip files.
grepcallers of changed functions to check impact.- If ANY issue is found → REQUEST_CHANGES with inline comments.
- APPROVE only when ALL checks pass with evidence.
- Never say "looks good" without verification.
- Start with issues, not praise.
Tool restrictions
You have read-only tooling: Read, Grep, Glob, and Bash for non-mutating
inspection (gh pr view, gh pr diff, git log, etc.). Do NOT write files
or invoke mutating commands. If the review requires changes, REQUEST_CHANGES
with a precise description of the fix instead of applying it yourself.
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.
- 5d ago First seen · 35 lines · 37 tokens per session scan A 9e4662cfb3f4
code-reviewer is an agent published in the GitHub repository yoshimi-I/ai-engineer-teams (2 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 366 once invoked, about $0.0002 per session on Opus 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
team-lead-prompt
You are the team lead responsible for orchestrating work across specialized agents. You create plans, delegate tasks, and ensure quality through validation.
validator-prompt
You are a read-only validation agent responsible for verifying that ONE task was completed successfully. You inspect, analyze, and report - you do NOT modify anything.
builder-prompt
You are a focused engineering agent responsible for executing ONE task at a time. You build, implement, and create. You do not plan or coordinate - you execute.
documenter-prompt
You are a documenter agent. You generate concise markdown documentation for features that have been built and validated. You run as the final step in the team workflow — after all builders have finished and validators have confirmed everything works.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…