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/epicsagas/epic-harness/orchestratenpx skills add epicsagas/epic-harness --skill orchestrategit clone --depth 1 https://github.com/epicsagas/epic-harnessWrote 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/epicsagas/epic-harness/orchestrate)<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>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 5.1 | $0.00035 | $0.02334 |
| Opus 5 | $0.00017 | $0.01167 |
| Sonnet 5 | $0.00007 | $0.00467 |
| Haiku 4.5 | $0.00003 | $0.00233 |
Grade B, and why
orchestrate scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
{read control.json; show directives if any, else "none"} How it starts
The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Orchestrate
CRITICAL: Run HARNESS_DIR=$(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
- Run
HARNESS_DIR=$(epic-harness path) - Read
$HARNESS_DIR/orchestrator/run.json - If no active run, this skill does not apply — return
Step 2: Read agent inbox
- Read
$HARNESS_DIR/orchestrator/agents/{my_id}/inbox.jsonl - Process any pending messages from other agents or user interventions
- Messages from other agents: integrate into current task context
- Messages from user (via intervene redirect): adjust task accordingly
Step 3: Check control directives
- Read
$HARNESS_DIR/orchestrator/control.json - 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
- After acting on a directive, increment
generationin control.json to acknowledge
Step 4: Check dependencies
- Read
$HARNESS_DIR/orchestrator/run.jsondependency graph - Identify which agents this agent depends on
- Read their
status.json— if any dependency is not DONE, wait - If all dependencies are DONE, proceed with task
Step 5: Execute with progress reporting
While working on the assigned task:
- The Rust
orchestratehook automatically appends events tostream.jsonlon each tool call - Status updates happen automatically via the hook
- No manual progress reporting needed — the hook handles it
Step 6: Complete and hand off
When task is complete:
- Report status via structured output format (DONE/DONE_WITH_CONCERNS/BLOCKED/NEEDS_CONTEXT)
- The
orchestratehook will evaluate dependencies and notify downstream agents - If results should be shared with specific agents, include in the output summary
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.
- 6d ago First seen · 248 lines · 35 tokens per session scan B bc02fff0a9f0
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.
Other skills, from other repositories
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
duckduckgo-search
Free keyless web, news, and image search via ddgs.
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.