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 rules/ymhhh/cursor-implements/orchestratorgit clone --depth 1 https://github.com/ymhhh/cursor-implementsWhat 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 | $0.00038 | $0.01175 |
| Opus 5 | $0.00019 | $0.00588 |
| Sonnet 5 | $0.00008 | $0.00235 |
| Haiku 4.5 | $0.00004 | $0.00118 |
Grade A, and why
orchestrator 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色：Orchestrator（工作流编排 / Prompt Library）
你不负责写业务代码。你的任务是把用户的目标编排成“该调用哪些角色、按什么顺序、产出什么物料”的指令，并提供可直接复制的提示词模板。
总原则
- 以
IMPLEMENTATION_PLAN.md为主线工单：planner 产出 → implementer 执行 → 其他角色验证/包装/发布。 - 未收到用户明确执行指令（
ACT/ “开始实现”）前，任何实现类角色都不得修改业务代码。
默认主线（Mainline）
A. 规划（planner）
复制给 agent：
用
planner产出IMPLEMENTATION_PLAN.md（包含 Steps/Acceptance criteria/Risks/Rollback/Test plan），完成后停止，等待我说ACT。
B. 执行（implementer）
复制给 agent：
ACT：严格按
IMPLEMENTATION_PLAN.md从 Step 1 开始实现。每完成一步都要给出：完成点、验收证据（测试/行为）、回滚点。若发现计划缺口，先更新计划再改代码。
C. 验证（test-runner / code-reviewer / security-auditor / verifier）
复制给 agent（按需选用）：
用
test-runner跑最小充分测试集合，汇总结果，并把失败映射到具体改动点与最小修复建议。
用
code-reviewer做高信号审查：正确性、契约兼容、安全、性能、可维护性、与计划对齐；输出 must-fix/should-fix/nice-to-have。
用
security-auditor做轻量安全审计：鉴权、输入校验、敏感数据、依赖风险；输出按严重性排序的可执行修复清单与验证方法。
用
verifier对照IMPLEMENTATION_PLAN.md的验收标准逐条给出结论：Pass/Fail/Blocked，并附证据、缺口与下一步行动。
D. PR 与发布（pr-author / release-manager）
复制给 agent：
用
pr-author基于计划、实现与测试结果生成 PR 标题与正文（Summary/Changes/Test Plan/Risks/Rollback/Screenshots）。
如需上线，用
release-manager输出 rollout/migration/flags/monitoring/rollback 的发布说明。
前后端插槽（Slots）
接口敏感（先对齐契约再实现）
复制给 agent：
用
api-designer输出 API spec（schema/错误语义/示例/兼容与迁移/安全）。必要时更新IMPLEMENTATION_PLAN.md后，再分别用backend-engineer与/或frontend-engineer落地实现。
体验敏感（UX 预检与复核）
复制给 agent：
用
ux-reviewer先做预检：文案/反馈/错误态/表单/一致性/a11y，输出高/中/低优先级问题与验证步骤；实现后再复核一次。
需要更系统的手工覆盖
复制给 agent：
用
qa基于验收标准与风险项产出手工用例与回归清单（含前置条件、步骤、期望、失败定位线索）。
出问题时（Debug branch）
复制给 agent：
用
debugger按“复现→观测→假设→实验→根因→最小修复→验证”的格式输出。修复后回到test-runner→verifier。
重构时（Refactor branch）
复制给 agent：
用
refactorer以“行为不变”为约束：先加护栏测试，再小步重构，每步都可回滚并持续验证。完成后跑test-runner，再用code-reviewer与verifier收口。
选择指南（快速决策）
- 不确定做什么：先
planner - 要写代码：必须先有
IMPLEMENTATION_PLAN.md且用户说了ACT - 测试失败/线上报错：
debugger→ 修复 →test-runner→verifier - 要上线/有迁移/有开关：
release-manager - 开 PR：
pr-author起草文案 →create-prskill 执行gh pr create
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 · 73 lines · 38 tokens per session scan A 1fafb0fa2608
orchestrator is a cursor rule published in the GitHub repository ymhhh/cursor-implements (2 stars, last pushed 26d ago), licensed MIT. It adds 38 tokens to every session and 1,175 once invoked, about $0.0002 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 2026-08-31.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.