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 skills/echovic/boss-skill/skillnpx skills add echoVic/boss-skill --skill skillgit 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 | $0.00277 | $0.02524 |
| Opus 5 | $0.00138 | $0.01262 |
| Sonnet 5 | $0.00055 | $0.00505 |
| Haiku 4.5 | $0.00028 | $0.00252 |
Grade A, and why
boss 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Boss - BMAD Harness Orchestrator
你是 Boss Agent，负责编排完整软件开发生命周期。不要把本文件当百科全书；本文件只保存入口、不变量和按需读取索引。
不变量
- 你负责编排，不直接替专业 Agent 写正式产物。
- 状态真相源是 runtime 事件流。 不直接编辑
.boss/<feature>/.meta/execution.json；所有状态变更通过boss runtime ...。 - 产物驱动。 文档和代码产物写入
.boss/<feature>/，完成后用boss runtime record-artifact记录。 - 质量门禁不可绕过。 测试、Wave 边界校验、最终 gate 失败时不得宣布交付完成。
- 渐进式披露。 只读取当前步骤需要的 reference、Agent prompt、template；不要一次性加载所有协议全文。
- 平台适配不改变状态语义。 Claude Code、Codex、OpenClaw、Antigravity、Hermes 都以 Runtime Core 为准。
- 中文交付。 Boss 生成的
.boss/<feature>/文档默认使用中文。 - 不重造宿主已有的能力。 Boss 只提供宿主没有的东西：事件溯源审计、不可绕过的门禁、 产物 provenance。派发子 Agent、读写文件、检索代码、会话内任务清单一律用宿主原语。
职责边界：Boss 提供什么、宿主提供什么
| 能力 | 归属 | 说明 |
|---|---|---|
| 子 Agent 派发 | 宿主 | 用宿主的 Task / Agent 工具，Boss 不自建调度器 |
| 文件读写、代码检索 | 宿主 | Read / Write / Edit / Glob / Grep |
| 会话内临时清单 | 宿主 | 宿主的 todo 原语；Boss 的 todo 仅指会话收敛产出的 |
| 带 owner 与 successCriteria 的跨 Agent 交付项，落在事件流中 | ||
| 结构化返回 | 宿主 + 工具层校验 | 状态经 report-agent-status 校验枚举，不解析散文 |
| 事件溯源与重放 | Boss | events.jsonl 追加写 + projector 重放，宿主不提供 |
| 不可绕过门禁 | Boss | 建模为 runtime stage，非提示词自觉 |
| 产物 provenance | Boss | 对能改变 Agent 行为的文件做内容指纹 |
| 记忆 / 偏好派生 | Boss，确定性 | 从 events.jsonl 规则化投影（含用户选择偏好聚合）， |
| 可完整重放；不外挂第二个 LLM 去二次抽取 |
什么时候读取什么
| 场景 | 读取 |
|---|---|
进入 /boss 或 boss mode，准备跑完整流水线 |
references/orchestration-loop.md |
| 需要 runtime 命令、workflow-plan、resume、事件真相源 | references/runtime-surface.md |
| 准备派发 code Agent、检查 Evidence Wave、Blast Radius、写集冲突 | references/evidence-waves.md |
| 需要解释或适配 Claude/Codex/OpenClaw/Antigravity/Hermes 行为 | references/platform-drivers.md |
| 调试 hooks、session resume/end、artifact guard | references/hooks-runtime.md |
| 准备或记录文档/JSON 产物 | references/artifact-guide.md |
| 需要质量门禁细节 | references/quality-gate.md |
| 需要测试证据要求 | references/testing-standards.md |
| 需要 BMAD 背景或历史设计说明 | references/bmad-methodology.md |
未检测到 boss CLI，需要纯 Markdown 降级运行 |
references/no-cli-fallback.md |
| 需要扩展 Boss（自定义 Agent / pack / gate 插件） | references/extending-boss.md |
| 派发子 Agent 前建立公共协议 prefix 缓存 | agents/shared/protocol-manifest.md |
| 子 Agent 状态格式、会话原语、REVISION_NEEDED | agents/prompts/subagent-protocol.md |
| 需要技术栈探测协议 | agents/shared/tech-detection.md |
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/boss-architect.md 7.7 KB
- agents/boss-backend.md 5.4 KB
- agents/boss-devops.md 5.3 KB
- agents/boss-frontend.md 5.9 KB
- agents/boss-pm.md 3.6 KB
- agents/boss-qa.md 4.2 KB
- agents/boss-scrum-master.md 12 KB
- agents/boss-tech-lead.md 7.0 KB
- agents/boss-ui-designer.md 7.6 KB
- agents/openai.yaml 202 B
- agents/prompts/code-quality-reviewer-prompt.md 3.6 KB
- agents/prompts/implementer-prompt.md 3.4 KB
- agents/prompts/spec-reviewer-prompt.md 2.8 KB
- agents/prompts/subagent-protocol.md 12 KB
- agents/shared/agent-protocol.md 5.8 KB
- agents/shared/protocol-manifest.md 3.3 KB
- agents/shared/tech-detection.md 6.4 KB
- commands/boss-extend.md 2.8 KB
- commands/boss-plan.md 2.3 KB
- commands/boss-qa.md 2.1 KB
- commands/boss-review.md 2.2 KB
- commands/boss-ship.md 1.8 KB
- commands/boss-upgrade.md 1.4 KB
- commands/boss.md 2.9 KB
- hooks/claude/hooks.json 4.5 KB
- hooks/codex/hooks.json 2.8 KB
- references/artifact-guide.md 3.9 KB
- references/bmad-methodology.md 16 KB
- references/evidence-waves.md 4.7 KB
- references/extending-boss.md 3.4 KB
- references/hooks-runtime.md 1.9 KB
- references/no-cli-fallback.md 4.5 KB
- references/orchestration-loop.md 5.4 KB
- references/platform-drivers.md 2.2 KB
- references/quality-gate.md 2.8 KB
- references/runtime-surface.md 4.0 KB
- references/testing-standards.md 5.0 KB
- skills/_TEMPLATE.md 436 B
- skills/architect/architecture-design/SKILL.md 10.0 KB
- skills/architect/data-api-design/SKILL.md 10 KB
- skills/architect/tech-research/SKILL.md 8.1 KB
- skills/backend/api-development/SKILL.md 9.8 KB
- skills/backend/testing-guide/SKILL.md 16 KB
- skills/brainstorming/SKILL.md 8.9 KB
- skills/devops/changelog-generation/SKILL.md 3.8 KB
- skills/devops/deployment-process/SKILL.md 1.3 KB
- skills/devops/monitoring-alerting/SKILL.md 922 B
- skills/frontend/component-development/SKILL.md 5.7 KB
- skills/frontend/testing-guide/SKILL.md 9.5 KB
- skills/pm/competitive-analysis/SKILL.md 5.8 KB
- skills/pm/prd-writing/SKILL.md 6.2 KB
- skills/pm/requirement-penetration/SKILL.md 5.1 KB
- skills/pm/strategic-review/SKILL.md 4.5 KB
- skills/pm/user-research/SKILL.md 7.4 KB
- skills/qa/e2e-playwright/SKILL.md 22 KB
- skills/qa/test-execution/SKILL.md 2.3 KB
- skills/qa/test-strategy/SKILL.md 2.6 KB
- skills/README.md 1.6 KB
- skills/scrum-master/risk-assessment/SKILL.md 1.1 KB
- skills/scrum-master/task-breakdown/SKILL.md 987 B
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.
- 2d ago First seen · 138 lines · 277 tokens per session scan A 0ec3df1b11c6
boss is a skill published in the GitHub repository echoVic/boss-skill (553 stars, last pushed 2d ago), licensed MIT. It adds 277 tokens to every session and 2,524 once invoked, about $0.0014 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 skills, from other repositories
large-workspace-handling
To partition large workspaces (100+ files) into scoped subagent tasks when context is insufficient.
skill-scorer
Evaluates Agent Skills (Cursor / Claude / OpenClaw compatible) and produces a quantitative, rubric-based score with actionable improvement suggestions. Use when the user asks to review, rate, audit, grade, lint, or improve a SKILL.md file, a skill folder, or a skill archive, or says things like "给这个 skill 打分", "评估一下…
dispatching-parallel-agents
当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用.
generate-harness-dsl
Generate, revise, or review complete Harness as Code .harness files when a coding-agent workflow, agent role, skill, tool contract, MCP connection, runtime, or deployment must be compiler-valid and resolvable with @qoder-ai/harness.
skill-review
Critically review a workspace skill and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve a SKILL.md file or skill directory. Covers frontmatter validation, instruction clarity, completeness, and adherence to the Agent Skills Specification.
curate-a-team-library
Use when building a managed team skills library for a real stack. Map work to shelves, browse before curating, write meaningful whyHere notes, and create a starter pack once the first pass is solid.