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-extendgit 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-extend)<a href="https://agentmods.dev/commands/echovic/boss-skill/boss-extend"><img src="https://agentmods.dev/badge/commands/echovic/boss-skill/boss-extend.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 | $0.00053 | $0.00875 |
| Opus 5 | $0.00026 | $0.00438 |
| Sonnet 5 | $0.00011 | $0.00175 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade A, and why
boss:extend 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
/boss:extend — 引导式扩展 Boss
/boss:extend 引导用户在当前项目里加一个自定义扩展,无需读源码。产出落到项目级扩展点,/boss 下次运行时自动发现。
这是 Boss 的自我繁殖层:像 superpowers 的
writing-skills一样,让生态自己长。
能扩展什么
| 类型 | 落地位置 | 用途 |
|---|---|---|
| 自定义 Agent | .boss/plugins/<name>/ |
加一个新角色(如 Security Reviewer、Data Engineer) |
| Pipeline Pack | .boss/pipeline-packs/<name>/ |
定制阶段/角色组合(如只跑 backend + qa) |
| Gate 插件 | .boss/plugins/<name>/ |
加一道自定义质量门禁 |
执行步骤
- 读取
references/extending-boss.md取得扩展契约与 schema。 - 一次一个问题,确认:扩展类型 + 名称 + 触发/挂载时机。
- 按对应模板生成文件(见下)。
- 校验:
- Pack →
boss packs detect <dir> --json应能列出新 pack(有 CLI 时)。 - Plugin →
boss runtime register-plugins <feature>应发现它(有 CLI 时)。 - 无 CLI → 提示用户文件已就位,
/boss会按references/no-cli-fallback.md手动加载。
- Pack →
- 输出:新扩展路径 + 如何在
/boss中启用。
Pipeline Pack 模板
{
"name": "<pack-name>",
"version": "1.0.0",
"type": "pipeline-pack",
"description": "<一句话说明>",
"author": "<you>",
"license": "MIT",
"when": { "fileExists": ["package.json"], "noFileExists": [] },
"priority": 3,
"config": {
"stages": [1, 2, 3, 4],
"roles": "custom",
"agents": ["boss-pm", "boss-architect", "boss-backend", "boss-qa"],
"gates": ["gate0", "gate1"],
"agentStages": { "boss-pm": 1, "boss-architect": 1, "boss-backend": 3, "boss-qa": 3 }
},
"enabled": true
}
Gate 插件模板
{
"name": "<gate-name>",
"version": "1.0.0",
"type": "gate",
"description": "<一句话说明>",
"author": "<you>",
"license": "MIT",
"hooks": { "gate": "gate.js" },
"config": { "passThreshold": 0.7 },
"stages": [3],
"enabled": true
}
配套 gate.js 契约见 references/extending-boss.md。
自定义 Agent 模板
以 agents/boss-*.md 为范式,产出 .boss/plugins/<name>/agent.md:角色定位、输入产物、输出产物、状态报告(沿用 DONE/BLOCKED/REVISION_NEEDED 协议)。
用法
/boss:extend # 引导式选择类型
/boss:extend pack backend-only # 直接建一个 pack
/boss:extend agent security # 直接建一个 agent
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 · 85 lines · 53 tokens per session scan A 5ed6426d3588
boss:extend is a command published in the GitHub repository echoVic/boss-skill (553 stars, last pushed 5d ago), licensed MIT. It adds 53 tokens to every session and 875 once invoked, about $0.0003 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
upgrade
Upgrade the skillshare CLI binary and/or the built-in skillshare skill.
init
Initialize configurations for Supabase local development.
tokenless-stats
Show Tokenless compression statistics.
migrate
Command "migrate" from chohra-med/expo_boilerplate, covering invocation, steps and rule.
release
Walk the llmwiki release process step by step.
add-agent
引导新增一个 Agent 适配器。用法 /add-agent.