Borrowing it
Nothing to install: this file belongs to BambooGap/skills-orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/BambooGap/skills-orchestrator/main/AGENTS.mdgit clone --depth 1 https://github.com/BambooGap/skills-orchestratorWrote 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/instructions/bamboogap/skills-orchestrator/agents-md)<a href="https://agentmods.dev/instructions/bamboogap/skills-orchestrator/agents-md"><img src="https://agentmods.dev/badge/instructions/bamboogap/skills-orchestrator/agents-md/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/instructions/bamboogap/skills-orchestrator/agents-md"><img src="https://agentmods.dev/badge/instructions/bamboogap/skills-orchestrator/agents-md.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 | $0.00927 | $0.00927 |
| Opus 5.5 | $0.00371 | $0.00371 |
| Sonnet 5.5 | $0.00185 | $0.00185 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
skills-orchestrator AGENTS.md 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 2mo 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Required Skills
以下 skills 为强制加载，所有任务均须遵循。
当前 Zone 无强制 skills。
Available Skills
以下 skills 按需选用。根据当前任务选择最相关的 skill 加载。
| Skill | 说明 | Tags |
|---|---|---|
| 安全重构 | 安全重构步骤：小步快走、先写测试、提取函数、消除重复代码 | refactor, quality |
| 系统化调试 | 用于调试 bug、测试失败、异常排查，提供结构化的排查步骤 | debug, error, testing |
| PR Review | Systematic PR review process with blocking/suggestion/nit severity levels | review, english |
| 安全代码审查 | OWASP Top 10 快速核查：输入验证、认证、注入、敏感数据暴露 | review, security, owasp |
| 测试驱动开发 | Red-Green-Refactor 循环：先写失败测试，再写最小实现，再重构 | testing, coding, tdd, quality |
| 部署检查清单 | 上线前强制检查：功能验证、回滚方案、监控告警、数据库变更顺序 | ops, deployment, checklist, production |
| 错误处理规范 | 分层错误处理：业务错误 vs 技术错误，不吞异常，不过度防御 | coding, error, reliability |
| API 设计规范 | REST API 设计：资源命名、状态码、版本控制、错误格式统一 | coding, api, design, rest |
| 完成分支清单 | 提 PR 前的完整检查清单：代码质量、测试、commit 历史、PR 描述、文档 | git, pr, checklist |
| Git Worktrees 工作流 | git worktree 使用方法，同时在多个分支工作，无需 stash 或切换分支 | git, workflow, parallel |
| 性能优化方法论 | 先测量再优化：profiling 定位瓶颈，避免过早优化，量化改进效果 | quality, performance, profiling, optimization |
| 环境管理规范 | 开发/测试/生产三环境隔离：配置管理、密钥安全、环境一致性 | ops, environment, config, security |
| 代码风格规范 | 命名、函数大小、注释时机：让代码自解释，减少认知负担 | coding, style, naming, readability |
| 结构化头脑风暴 | 开始编码前充分展开问题，发散-收敛-压力测试，避免过早收敛到第一个方案 | planning, design, decision |
| 任务估时规范 | 拆解到叶节点再估时，用三点估计，显式列出不确定性 | planning, estimation, project |
| 写实现计划 | 编码前制定实现计划：影响范围、步骤拆解、测试计划、风险评估 | planning, process |
| 写文档 | README 规范、代码注释时机、API 文档格式、迁移文档模板 | docs, readme, api |
| Git 提交规范 | 基于 git-operations 扩展的提交信息规范，强调 Conventional Commits 格式 | git, commit, convention |
| Git 操作规范 | 常用 git 操作规范：提交信息格式、分支命名约定、PR 描述模板 | git, base |
Runtime Skill Loading
AGENTS.md 是启动引导，不会在当前会话中热更新。 如当前环境已配置 Skills Orchestrator MCP，每个新任务开始或任务目标明显变化时：
- 调用
prepare_context({"task": "<用户任务>"})获取本轮 active_skills。 - 本轮只遵循 active_skills；之前任务加载过但本次未返回的 skills 视为 inactive。
- 如需单个完整 Skill，可调用
get_skill({"id": "<skill-id>"})。 - 多步骤任务优先使用
pipeline_start/pipeline_advance。
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.
- 2mo ago First seen · 45 lines · 927 tokens per session scan A 2b1970343008
skills-orchestrator AGENTS.md is an instructions file published in the GitHub repository BambooGap/skills-orchestrator (4 stars, last pushed 1mo ago), licensed MIT. It adds 927 tokens to every session, about $0.0037 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 2026-08-31.
skills-orchestrator AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skills-orchestrator AGENTS.mdBambooGap/skills-orchestrator | Instructions file | 4 | 1mo ago | MIT | A | 927 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |