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-plangit clone --depth 1 https://github.com/echoVic/boss-skillWhat 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 | $0.00051 | $0.00726 |
| Opus 5 | $0.00026 | $0.00363 |
| Sonnet 5 | $0.00010 | $0.00145 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
boss:plan 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.
What it actually says
/boss:plan — 单环节：规划（PM + Architect）
/boss:plan 是 Boss 流水线的规划环节独立入口。你不需要跑完整 9 Agent，就能拿到一份可追溯的 PRD + 架构设计。适合「先想清楚再动手」或「给已有项目补一份架构文档」。
这是
/boss的一个切片，不是另一套逻辑。底层复用同一套 agent prompt、runtime 与产物目录，只是把入口收窄到 stage 1。
适合 / 不适合
适合 /boss:plan |
用完整 /boss |
|---|---|
| 只想要 PRD + 架构，先评估再决定做不做 | 想一路做到可运行/可部署 |
| 给已有代码库补规划文档 | 需要开发 + 测试 + 部署证据 |
| 规划完人工接手实现 | 需要门禁与 QA 证据链 |
执行步骤
- 读取
SKILL.md取得不变量与路由；本命令只执行到 stage 1 结束。 - Feature slug 归一化（见
references/orchestration-loop.mdStep 0a）。约束类输入不新建目录。 - 除非
--quick，按references/orchestration-loop.mdStep 0 做需求澄清（缺「做什么/给谁用/核心场景」时读取skills/brainstorming/SKILL.md）。 - 初始化：
boss project init <feature-name>（无 CLI 时按references/no-cli-fallback.md退化为纯 markdown）。 - 按 DAG 派发 PM（
agents/boss-pm.md）产出prd.md，再派发 Architect（agents/boss-architect.md）产出architecture.md。 - 每份产物完成后
boss runtime record-artifact <feature> <artifact> 1。 - 停在 stage 1 完成确认节点，不进入 tech-review / 开发。输出：产物路径 + 下一步建议（可接
/boss:review或完整/boss --continue-from 2）。
用法
/boss:plan 做一个面向设计师的素材管理工具
/boss:plan 给现有 API 补一份架构设计 --skip-ui
/boss:plan 用户认证模块 --quick
选项
| 参数 | 说明 |
|---|---|
--skip-ui |
跳过 UI 设计，只产出 PRD + 架构 |
--quick |
跳过需求澄清与确认节点 |
--lang <zh|en> |
产出文档语言（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.
- yesterday First seen · 46 lines · 51 tokens per session scan A 4d8ed916cee9
boss:plan is a command published in the GitHub repository echoVic/boss-skill (552 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 726 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.
tokenless-stats
Show Tokenless compression statistics.
cost-tracker
Track session costs, understand token spend, and get optimization tips.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.
t800-onboard
Для чата с новичками. Показывает, что настроено в Cursor (global + local), и что умеет отдел T-800.
session-log
Create or append a session log entry.