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/movebrickschi/harness-engineering-mcp/02-agent-orchestrationgit clone --depth 1 https://github.com/movebrickschi/harness-engineering-mcpWrote 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/rules/movebrickschi/harness-engineering-mcp/02-agent-orchestration)<a href="https://agentmods.dev/rules/movebrickschi/harness-engineering-mcp/02-agent-orchestration"><img src="https://agentmods.dev/badge/rules/movebrickschi/harness-engineering-mcp/02-agent-orchestration.svg" alt="Measured on agentmods" 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 | $0.01040 | $0.01040 |
| Opus 5 | $0.00520 | $0.00520 |
| Sonnet 5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
02-agent-orchestration 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 3d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Agent Swarm Orchestration
When to Activate
When the user's message contains any of these trigger phrases, immediately read and follow the orchestrator skill at .cursor/skills/orchestrator/SKILL.md:
- "编排模式" — general orchestration (feature, refactor, or auto-detect)
- "开发并测试" — develop and test a feature
- "修复并测试" — fix a bug and test the fix
- "编排修复" — orchestrated bug fix
- "全流程" — full pipeline (all agents)
- "测试：" — test only, skip dev agents
- "补充测试" — test only, skip dev agents
- "写测试" — test only, skip dev agents
Scenario Detection
If the trigger phrase alone does not clarify the scenario, infer from context:
| Signal | Scenario |
|---|---|
| Words like "bug", "报错", "失败", "异常", "修复", "fix" | Bug Fix |
| Words like "重构", "refactor", "优化结构" | Refactor |
| Words like "测试：", "补充测试", "写测试", "test only" | Test Only (skip dev agents, only run test agent) |
| Everything else (new endpoint, new page, new feature) | New Feature |
Agent Roster
All agents are tech-stack agnostic — they auto-detect the project's languages, frameworks, and conventions before doing any work.
| Agent | Role | Dispatch Timing |
|---|---|---|
frontend-agent |
Client-side / UI development | Step 2: 并行开发（按需） |
backend-agent |
Server-side / API development | Step 2: 并行开发（按需） |
dev-agent |
General-purpose fallback | Step 2: 当前后端无法分离时 |
review-agent |
Code quality review（只读） | Step 3: 与 test-agent 并行 |
test-agent |
Test writing & execution | Step 3: 与 review-agent 并行 |
doc-agent |
Documentation generation | Step 5: 最后执行 |
Mandatory First Step: Tech Stack Detection
The orchestrator MUST auto-detect the project's tech stack before dispatching any agent. This includes:
- Languages and frameworks (frontend + backend)
- Test frameworks per module
- Package manager
- Monorepo structure (if applicable)
- Immutable files (database schemas, API contracts, generated code)
- Code style configuration
This Project Context is passed to every subagent.
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.
- 3d ago First seen · 99 lines · 1,040 tokens per session scan A 51cc40767c63
02-agent-orchestration is a cursor rule published in the GitHub repository movebrickschi/harness-engineering-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,040 tokens to every session, about $0.0052 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.