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/votruongdanh/skills-agent/orchestrategit clone --depth 1 https://github.com/VoTruongDanh/Skills-AgentWrote 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/votruongdanh/skills-agent/orchestrate)<a href="https://agentmods.dev/rules/votruongdanh/skills-agent/orchestrate"><img src="https://agentmods.dev/badge/rules/votruongdanh/skills-agent/orchestrate.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 | $0.00053 | $0.00900 |
| Opus 5 | $0.00026 | $0.00450 |
| Sonnet 5 | $0.00011 | $0.00180 |
| Haiku 4.5 | $0.00005 | $0.00090 |
Grade A, and why
orchestrate 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Protocol
START: Read .ai-memory.md from project root. Check project architecture, team structure, past orchestration plans, ongoing tasks, and blockers.
END: Update .ai-memory.md using Memory Compaction Rules with: workstreams, assignments, dependencies, execution order, and blockers/risks.
Goal
Break a complex request into a coordinated execution plan with clear agent assignments.
Agent Routing
- Primary coordinator → read
.kiro/skills/agents/agents/orchestrator.mdand apply its knowledge - For planning phases → read
.kiro/skills/agents/agents/project-planner.mdand apply its knowledge - For each workstream, read the most relevant agent file:
- Frontend tasks → read
.kiro/skills/agents/agents/frontend-specialist.md - Backend tasks → read
.kiro/skills/agents/agents/backend-specialist.md - Database tasks → read
.kiro/skills/agents/agents/database-architect.md - Testing → read
.kiro/skills/agents/agents/test-engineer.md - Security review → read
.kiro/skills/agents/agents/security-auditor.md - Deployment → read
.kiro/skills/agents/agents/devops-engineer.md
- Frontend tasks → read
Socratic Gate
Before orchestrating, verify:
- What is the full objective? (end-to-end scope)
- How many domains are involved? (frontend, backend, DB, infra?)
- Are there hard dependencies or deadlines? If any answer is unclear, ASK before proceeding.
Workflow
- Read Memory — Load
.ai-memory.mdfor project context and history. - Decompose the objective into workstreams.
- Assign each workstream to the appropriate agent/role.
- Identify dependencies, blockers, and the critical path.
- Define parallelizable tasks and merge points.
- Produce an execution order with clear handoffs.
- Quality Gate — Read
.kiro/skills/_scripts/checklist.mdand verify each workstream output before merge. - Update Memory — Save orchestration plan to
.ai-memory.md.
Output format
- Objective
- Workstreams (with assigned agents)
- Dependencies and critical path
- Execution order (sequential + parallel)
- Risks and mitigations
- Done criteria for each workstream
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 Changed · +3 lines e2c553b159b1
- 5d ago First seen · 78 lines · 53 tokens per session scan A 7965de616ade
orchestrate is a cursor rule published in the GitHub repository VoTruongDanh/Skills-Agent (2 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 900 once invoked, about $0.0003 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
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.