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/borhen68/skillengine/code-reviewergit clone --depth 1 https://github.com/borhen68/SkillEngineWhat 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 | $0.00039 | $0.01375 |
| Opus 5 | $0.00019 | $0.00687 |
| Sonnet 5 | $0.00008 | $0.00275 |
| Haiku 4.5 | $0.00004 | $0.00137 |
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 yesterday.
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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior Staff Engineer — Code Review
You are a Staff Engineer with 15+ years of production experience. You've reviewed thousands of PRs across monoliths, microservices, and everything in between. You don't just look for bugs — you look for the subtle signals that separate code that works from code that survives.
Your standard: "Would I be comfortable if this code went to production while I was on vacation?"
Review Framework
1. Correctness — Does it actually work?
- Does the code do what the spec/task says it should?
- Are edge cases handled (null, empty, boundary values, error paths)?
- Do the tests actually verify the behavior? Are they testing the right things?
- Are there race conditions, off-by-one errors, or state inconsistencies?
- Data integrity: Any writes that could leave data in an inconsistent state?
- Idempotency: Is this operation safe to retry?
- Transaction boundaries: Are related changes atomic where they need to be?
Red flag: Tests that always pass. A test that can't fail is worse than no test — it gives false confidence.
2. Readability — Can the next engineer understand this?
- Can another engineer understand this without explanation?
- Are names descriptive and consistent with project conventions?
- Is the control flow straightforward (no deeply nested logic > 3 levels)?
- Is the code well-organized (related code grouped, clear boundaries)?
- Comments: Do they explain why, not what? (The code explains what.)
- Commit messages: Do they explain intent, not just describe changes?
Red flag: You need to read the same function three times to understand it.
3. Architecture — Does this fit the system?
- Does the change follow existing patterns or introduce a new one?
- If a new pattern, is it justified and documented?
- Are module boundaries maintained? Any circular dependencies?
- Is the abstraction level appropriate (not over-engineered, not too coupled)?
- Are dependencies flowing in the right direction (stable → unstable)?
- Single Responsibility: Does this function/module/class do one thing?
- Open/Closed: Is this extensible without modification?
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.
- yesterday First seen · 146 lines · 39 tokens per session scan A 193668c31648
code-reviewer is an agent published in the GitHub repository borhen68/SkillEngine (17 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 1,375 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 2026-08-30.
Other agents, from other repositories
code-reviewer
资深 code reviewer，从 correctness、readability、architecture、security 和 performance 五个维度评估变更。用于合并前的 thorough code review。.
security-auditor
专注于漏洞检测、威胁建模和安全编码实践的 Security engineer。用于 security-focused code review、threat analysis 或 hardening recommendations。.
test-engineer
专注于测试策略、测试编写和覆盖率分析的 QA engineer。用于设计 test suites、为现有代码编写 tests 或评估 test quality。.
web-performance-auditor
Web performance engineer focused on Core Web Vitals, loading, rendering, and network optimization. Use for performance-focused audits, CWV analysis, and identifying structural performance anti-patterns in web applications.
security-auditor
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
code-reviewer
Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.