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.
git 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-dev)<a href="https://agentmods.dev/commands/echovic/boss-skill/boss-dev"><img src="https://agentmods.dev/badge/commands/echovic/boss-skill/boss-dev/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/echovic/boss-skill/boss-dev"><img src="https://agentmods.dev/badge/commands/echovic/boss-skill/boss-dev.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00031 | $0.00710 |
| Opus 5.5 | $0.00012 | $0.00284 |
| Sonnet 5.5 | $0.00006 | $0.00142 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
boss:dev 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 today.
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:dev — 开发（Frontend + Backend）
/boss:dev 是专家小队的开发入口。派发 Frontend 和/或 Backend Agent 实现代码。
默认行为：开发完成后自动续跑 QA → Ship，除非用户主动叫停。
适合 / 不适合
适合 /boss:dev |
不适合 |
|---|---|
| 已有任务/架构，直接开始写代码 | 需求还不清晰（用 /boss:pm） |
| 给已有项目加新功能 | 只想做测试（用 /boss:qa） |
前置输入
- 优先读取
.boss/<slug>/tasks.md+.boss/<slug>/architecture.md - 若不存在，可用
prd.md或用户直接描述的需求替代
执行步骤
- Feature slug 归一化：确定 feature slug。
- 读取输入：优先读
tasks.md+architecture.md，其次prd.md，最后用户需求。 - 写集冲突检测：若有
tasks.md，检查任务间写集冲突，确定并行安全组。 - 风险确认：若 Blast Radius 命中强制确认 trigger，向用户确认后再派发。
- 派发开发 Agent：
- 有前端任务 → 读取
agents/boss-frontend.md，派发 Frontend Agent - 有后端任务 → 读取
agents/boss-backend.md，派发 Backend Agent - 前后端无写集冲突 → 可并行派发
- 开发 Agent 必须遵循 TDD：先写失败测试（RED）→ 最小实现（GREEN）→ 重构（REFACTOR）
- 有前端任务 → 读取
- Wave 边界校验：每个 Wave 完成后运行类型检查、lint、测试，不通过则修复。
- 自检：对照 Frontend/Backend 的硬性要求检查：
- TDD 验证清单全部勾选（RED 已验证、最小实现、全绿）
- 测试必须编写、覆盖率达标
- E2E 测试已编写
- 续跑：读取
references/continuation-chain.md，按链执行下一步（qa），除非用户叫停。
用法
/boss:dev user-auth
/boss:dev 给现有项目加支付功能
/boss:dev --stop-after dev
选项
| 参数 | 说明 |
|---|---|
--stop-after <环节> |
跑到指定环节后停（如 --stop-after dev 只开发不测试） |
--lang <zh|en> |
产物语言（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.
- today First seen · 58 lines · 31 tokens per session scan A 1c45972c7a69
boss:dev is a command published in the GitHub repository echoVic/boss-skill (544 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 710 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-28.
Other commands, from other repositories
implement
Execute tasks from a track's implementation plan following TDD workflow.
workflow-implement
Exécuter la phase d'Implémentation - développement TDD/BDD d'un sprint, d'un epic, d'une story ou de la file batch (séquentiel, ou parallèle via /team:sprint).
fix
Correction automatisee des bugs identifies par la QA Recette.
implement-approved-slice
Implement only the approved slice with minimal changes, then persist execution evidence in slice notes and TASKSTATE.md. The official execution path. Opt-in test-first mode via --tdd. Use when the plan and slice are approved, ambiguity is resolved and files in scope are known. Do not use during discovery or planning…
spec-impl
Execute spec tasks using TDD methodology.
implement
E2E-first Test driven development — unit tests written last.