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 commands/echovic/boss-skill/boss-reviewgit clone --depth 1 https://github.com/echoVic/boss-skillWrote 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/commands/echovic/boss-skill/boss-review)<a href="https://agentmods.dev/commands/echovic/boss-skill/boss-review"><img src="https://agentmods.dev/badge/commands/echovic/boss-skill/boss-review.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 | $0.00046 | $0.00678 |
| Opus 5 | $0.00023 | $0.00339 |
| Sonnet 5 | $0.00009 | $0.00136 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
boss:review 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 6d 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
/boss:review — 单环节：技术评审（Tech Lead）
/boss:review 是 Boss 流水线的评审环节独立入口。以 Tech Lead 身份对现有代码、架构或规划产物做技术评审与风险评估，产出 tech-review.md。只读评审，不改代码。
这是 gstack
/review的对应能力，但带 Boss 的可追溯产物：评审结论落在.boss/<feature>/tech-review.md，可被后续阶段或门禁引用。
适合 / 不适合
适合 /boss:review |
不适合 |
|---|---|
| 对已有代码/PR 做技术评审、风险打分 | 想让 agent 直接改代码（用 /boss 或直接编辑） |
评审 /boss:plan 产出的架构 |
需要跑测试证据（用 /boss:qa） |
| 上线前的技术风险 checklist | 纯代码解释问答（直接读） |
执行步骤
- 读取
SKILL.md取得不变量；本命令只执行 Tech Lead 评审，不派发开发/QA/DevOps。 - 确定评审目标：
- 有 feature slug 且
.boss/<feature>/存在 → 评审其prd.md/architecture.md/ 代码。 - 只给了代码路径或 PR → 归一化一个 slug，评审对应代码。
- 有 feature slug 且
- 读取
agents/boss-tech-lead.md与skills/tech-lead/code-review/SKILL.md、skills/tech-lead/technical-standards/SKILL.md。 - 以 Tech Lead 身份产出
tech-review.md（模板templates/tech-review.md.template）：技术选型合理性、风险等级、Blast Radius、必须修复项。 - 若挂在完整流水线上：
boss runtime record-artifact <feature> tech-review.md 2；独立使用时可只产出文档。 - 输出：评审结论、风险等级、阻塞项、建议下一步（可接
/boss:qa或/boss --continue-from 3）。
用法
/boss:review # 评审当前项目
/boss:review src/auth # 评审指定目录
/boss:review user-auth # 评审已有 .boss/user-auth 产物
选项
| 参数 | 说明 |
|---|---|
--lang <zh|en> |
评审文档语言（默认 zh） |
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.
- 6d ago First seen · 45 lines · 46 tokens per session scan A 2d8bade4ed1f
boss:review is a command published in the GitHub repository echoVic/boss-skill (553 stars, last pushed 6d ago), licensed MIT. It adds 46 tokens to every session and 678 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 commands, from other repositories
refactor-clean
You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its quality, maintainability, and performance.
gentle-sdd-ff
Fast-forward all SDD planning phases — proposal through tasks.
sdd-explore
Explore and investigate an idea or feature — reads codebase and compares approaches.
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
parallel-analyze
Multi-perspective analysis using parallel subagents. Analyzes code from architecture, security, performance, and testing viewpoints simultaneously.
parallel-review
Run parallel code review across multiple directories or files. Uses N subagents simultaneously for faster analysis.