epic-conductor

epic-conductor is a skill for Claude Code, Codex from ArcBlock/agent-skills. It costs 221 tokens per session (8,303 once invoked), scanned A, original, MIT.

A coordinator for delivering an entire epic, meaning a large feature made up of several related tasks. It assigns isolated agents to implement and verify each task, arranges independent reviews, handles fixes, and manages the final gates and merges.

In plain words
What is it for?
Breaking an epic into dependency-ordered sub-issues, dispatching workers, opening and reviewing pull requests, routing findings to fixers, and checking that no worker is still running before closeout.
Why use it?
It removes the need for one person to manually track task order, parallel workers, reviews, fixes, and merge readiness across a large feature.

Skill for Claude CodeCodex

Part of the agentloop plugin — 20 skills 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/arcblock/agent-skills/epic-conductor
Any agent
npx skills add ArcBlock/agent-skills --skill epic-conductor
Clone the repo
git clone --depth 1 https://github.com/ArcBlock/agent-skills

Made for: Claude Code, Codex.

Or install agentloop, the plugin that ships this one along with the rest of its 20 skills.

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 epic-conductor

README.md
[![agentmods](https://agentmods.dev/badge/skills/arcblock/agent-skills/epic-conductor.svg)](https://agentmods.dev/skills/arcblock/agent-skills/epic-conductor)
Your own site
<a href="https://agentmods.dev/skills/arcblock/agent-skills/epic-conductor"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/epic-conductor.svg" alt="Measured on agentmods" height="20"></a>
Per session 221 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,303 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00221 $0.08303
Opus 5 $0.00111 $0.04151
Sonnet 5 $0.00044 $0.01661
Haiku 4.5 $0.00022 $0.00830

Measured yesterday against content hash 8c07f1cbb307, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

epic-conductor 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 yesterday.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/assert-no-blocked-prs.test.ts, scripts/assert-no-blocked-prs.ts, scripts/assert-no-live-children.test.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/agentloop/skills/epic-conductor/SKILL.md · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

epic-conductor — drive a whole epic to merged, autonomously

Repo profile — read .claude/repo-profile.md first. This skill is repo-agnostic; the concrete gate commands (verification, e2e-gate, ui-verify, merge-gate) and identity-line script come from the consuming repo's profile. Where this doc names arc paths (.claude/verify/pre-pr.ts, merge-gate.ts, scripts/agent-identity.sh, scripts/gh-upload-media.sh) they are EXAMPLES — substitute the repo's own.

You are the conductor: a single resident session that turns one epic into a series of merged PRs by orchestrating a fleet of short-lived agents. You never write the feature code yourself — you decompose, dispatch, review-route, gate, and merge. You stay alive across the entire epic.

Hired factory/worker children still status=running (pid alive) make it forbidden to end_turn / close the session. Allowed: true closeout after each hire has GitHub evidence (PR URL or skip-comment) or the child was explicitly stopped. Watch pid + runs/*.json + cwd, not lastTurn alone. Before treating yourself as done:

bun "${AGENTLOOP_ROOT:-$HOME/.claude/plugins/marketplaces/arcblock-agent-skills/plugins/agentloop}/skills/epic-conductor/scripts/assert-no-live-children.ts" \
  --runs-dir "$(arc service status --print home 2>/dev/null || printf '%s' "$HOME")/.afs/code-agents/runs" \
  --ids <hired-id>,<hired-id>

Exit 0 only when none of those ids are live. Ghost status=running with a dead pid does not block (recover-territory). Factory cockpit rows are pid=-1; the watchdog must fail-closed on them (live, not ghost).

That watchdog covers live workers. Its artifact-side twin — no PR of yours left hanging on someone else's red — is the §9 closeout gate assert-no-blocked-prs.ts.

When this skill applies (and when it doesn't)

USE IT when: a human hands you an epic (or a decomposable body of multi-issue work) and wants it implemented end-to-end, and they remain reachable for high-level decisions ("safe default + object-if-wrong"), not per-step approval.

Read the full file on GitHub · 310 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday Changed 8c07f1cbb307
  2. 5d ago First seen · 310 lines · 221 tokens per session scan A fc6186866b96

Subscribe to this mod's changes

epic-conductor is a skill published in the GitHub repository ArcBlock/agent-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 221 tokens to every session and 8,303 once invoked, about $0.0011 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens