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/tianhanz/ears/orchestratenpx skills add tianhanz/ears --skill orchestrategit clone --depth 1 https://github.com/tianhanz/earsWrote 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/skills/tianhanz/ears/orchestrate)<a href="https://agentmods.dev/skills/tianhanz/ears/orchestrate"><img src="https://agentmods.dev/badge/skills/tianhanz/ears/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 | $0.00071 | $0.03237 |
| Opus 5 | $0.00036 | $0.01618 |
| Sonnet 5 | $0.00014 | $0.00647 |
| Haiku 4.5 | $0.00007 | $0.00324 |
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 4d 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 — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrate Skill
Coordinate multiple Claude Code sessions as an orchestrator. The orchestrator maintains strategic context and decision-making authority while spawning worker sessions to execute specific tasks in parallel.
Arguments: $ARGUMENTS
Concepts
-
Orchestrator: The main session (you) that maintains the big picture, makes decisions, and coordinates workers. Thinks like tianhanz — strategic, decisive, delegates execution but owns the judgment calls.
-
Worker: A spawned Claude Code session that executes a specific task. Workers write their progress and decisions to
.claude/state/session-<id>.yaml. When done, they mark status=completed with structured results. -
Session State: Structured YAML files in
.claude/state/that enable cross-session coordination. Each session writes its own state; the orchestrator reads all states. All writes are protected by file locking (fcntl) — safe for concurrent access. -
Failure Taxonomy: Workers report outcomes using a 5-category system:
success(task completed),blocked(waiting on external input/decision),env_failure(tooling/infra issue),timeout(exceeded time limit),inconclusive(unclear if done, needs human review).
Subcommands
/orchestrate plan
Plan the work breakdown and identify parallelizable tasks.
- Ask: "What's the overall goal? What are the major workstreams?"
- Identify tasks that can run in parallel (independent) vs sequential (dependent)
- For each parallelizable task, draft a worker prompt
- Output a dependency graph:
# Work plan with dependencies
tasks:
- id: task-1
description: "Review OTM radiation"
dependencies: [] # Can start immediately
estimated_complexity: low
worker_type: review # review | implement | test | research
- id: task-2
description: "Review SNB radiation"
dependencies: [] # Can run in parallel with task-1
estimated_complexity: medium
worker_type: review
- id: task-3
description: "Fix issues found in review"
dependencies: [task-1, task-2] # Blocked until reviews complete
estimated_complexity: high
worker_type: implement
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.
- 4d ago First seen · 353 lines · 71 tokens per session scan A 6cc6b3ace5b8
orchestrate is a skill published in the GitHub repository tianhanz/ears (5 stars, last pushed 4mo ago), licensed MIT. It adds 71 tokens to every session and 3,237 once invoked, about $0.0004 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 skills, from other repositories
agent-teams
Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.
orchestrate
This skill should be used when the user asks to 'orchestrate a task', 'break down work into parallel agents', 'coordinate subtasks', 'run agents in parallel', or mentions 'multi-agent'. Decomposes complex tasks into tracked subtasks, dispatches parallel subagents, and coordinates until completion.
agent-orchestration
Agent orchestration patterns for agentic loops, multi-agent coordination, alternative frameworks, and multi-scenario workflows. Use when building autonomous agent loops, coordinating multiple agents, evaluating CrewAI/AutoGen/Swarm, or orchestrating complex multi-step scenarios.
coding-agents-farm
To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.
cross-agent-handoff
Transfer context between AI agent sessions with structured handoff protocols, state serialization, and decision log preservation. Covers multi-agent coordination, context compression, and continuity patterns. Triggers on agent handoff, session transfer, or multi-agent continuity requests.
sema-mint
How to mint new sema patterns — the full pipeline from concept to content-addressed vocabulary entry. Covers required fields, dependency wiring, validation rules, and the hashing model.