orchestrate

orchestrate is a skill for Claude Code from epicsagas/epic-harness. It costs 35 tokens per session (2,334 once invoked), scanned B, original, Apache-2.0.

A coordination tool for active work split across multiple AI agents. It tracks messages, dependencies, status, and instructions for the shared run.

In plain words
What is it for?
Use it to read agent inboxes, resolve task dependencies, process control commands, and report or manage the state of a multi-agent run.
Why use it?
It prevents agents from missing handoffs, working before prerequisites are ready, or ignoring a pause, cancellation, or redirection.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the epic plugin — 28 skills, 6 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/epicsagas/epic-harness/orchestrate
Any agent
npx skills add epicsagas/epic-harness --skill orchestrate
Clone the repo
git clone --depth 1 https://github.com/epicsagas/epic-harness

Made for: Claude Code.

Or install epic, the plugin that ships this one along with the rest of its 28 skills, 6 hooks.

Wrote 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.

agentmods badge for orchestrate

README.md
[![agentmods](https://agentmods.dev/badge/skills/epicsagas/epic-harness/orchestrate.svg)](https://agentmods.dev/skills/epicsagas/epic-harness/orchestrate)
Your own site
<a href="https://agentmods.dev/skills/epicsagas/epic-harness/orchestrate"><img src="https://agentmods.dev/badge/skills/epicsagas/epic-harness/orchestrate.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,334 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.02334
Opus 5 $0.00017 $0.01167
Sonnet 5 $0.00007 $0.00467
Haiku 4.5 $0.00003 $0.00233

Measured 6d ago against content hash bc02fff0a9f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

orchestrate scanned grade B with 1 finding 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 6d 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

{read control.json; show directives if any, else "none"}
skills/orchestrate/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Orchestrate

CRITICAL: Run HARNESS_DIR=$(epic-harness path) first. NEVER use .harness/ in the project directory.

Mode: auto (default)

Triggered automatically when an active multi-agent orchestration is detected.

Step 1: Check orchestration state

  1. Run HARNESS_DIR=$(epic-harness path)
  2. Read $HARNESS_DIR/orchestrator/run.json
  3. If no active run, this skill does not apply — return

Step 2: Read agent inbox

  1. Read $HARNESS_DIR/orchestrator/agents/{my_id}/inbox.jsonl
  2. Process any pending messages from other agents or user interventions
  3. Messages from other agents: integrate into current task context
  4. Messages from user (via intervene redirect): adjust task accordingly

Step 3: Check control directives

  1. Read $HARNESS_DIR/orchestrator/control.json
  2. If a directive targets this agent (or "all"), act on it:
    • pause: halt work after current tool call, wait for resume
    • cancel: stop immediately, set status to "cancelled"
    • redirect: adopt the new instruction, discard current task
    • resume: resume from paused state
  3. After acting on a directive, increment generation in control.json to acknowledge

Step 4: Check dependencies

  1. Read $HARNESS_DIR/orchestrator/run.json dependency graph
  2. Identify which agents this agent depends on
  3. Read their status.json — if any dependency is not DONE, wait
  4. If all dependencies are DONE, proceed with task

Step 5: Execute with progress reporting

While working on the assigned task:

  1. The Rust orchestrate hook automatically appends events to stream.jsonl on each tool call
  2. Status updates happen automatically via the hook
  3. No manual progress reporting needed — the hook handles it

Step 6: Complete and hand off

When task is complete:

  1. Report status via structured output format (DONE/DONE_WITH_CONCERNS/BLOCKED/NEEDS_CONTEXT)
  2. The orchestrate hook will evaluate dependencies and notify downstream agents
  3. If results should be shared with specific agents, include in the output summary

Read the full file on GitHub · 248 lines

Changes

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.

  1. 6d ago First seen · 248 lines · 35 tokens per session scan B bc02fff0a9f0

Subscribe to this mod's changes

orchestrate is a skill published in the GitHub repository epicsagas/epic-harness (18 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 2,334 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.