epic-run

epic-run is a command for Claude Code from dtannen/pm. It costs 11 tokens per session (2,490 once invoked), scanned A, original, MIT.

A command that runs all tasks in a project epic, where an epic is a larger piece of work made up of related tasks. It checks dependencies and runs independent tasks in parallel through project-management tools.

In plain words
What is it for?
Use it to execute a named epic, discover its tasks, group tasks that can run together, and track locks, progress, and completion.
Why use it?
It removes the need to coordinate every task manually while preventing work from starting before its prerequisites are complete. Task locks and status updates help coordinate multiple workers.

Command for Claude Code

Part of the pm plugin — 4 skills, 13 commands, 5 agents, 3 hooks, 1 MCP server 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 commands/dtannen/pm/epic-run
Clone the repo
git clone --depth 1 https://github.com/dtannen/pm

Made for: Claude Code.

Or install pm, the plugin that ships this one along with the rest of its 4 skills, 13 commands, 5 agents, 3 hooks, 1 MCP server.

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-run

README.md
[![agentmods](https://agentmods.dev/badge/commands/dtannen/pm/epic-run.svg)](https://agentmods.dev/commands/dtannen/pm/epic-run)
Your own site
<a href="https://agentmods.dev/commands/dtannen/pm/epic-run"><img src="https://agentmods.dev/badge/commands/dtannen/pm/epic-run.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,490 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 $0.00011 $0.02490
Opus 5 $0.00005 $0.01245
Sonnet 5 $0.00002 $0.00498
Haiku 4.5 $0.00001 $0.00249

Measured 2d ago against content hash f78d1b1fcb76, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

epic-run 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 2d 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.

.claude-plugin/commands/epic-run.md · 338 lines

How it starts

The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Epic Execution with Maximum Parallelization

Execute an entire epic with intelligent dependency resolution and maximum parallel task execution using MCP orchestration.

Usage

/pm:epic-run <epic-name>

Example: /pm:epic-run knowledge-management-system

Instructions

You are launching the PM Epic Orchestrator - an intelligent system that executes entire epics with maximum parallelization while respecting task dependencies.

MCP Integration (Required)

Primary MCP tools for epic orchestration:

  • mcp__project-manager-mcp__list_epics - Find epic by name
  • mcp__project-manager-mcp__list_tasks - Get all tasks in epic
  • mcp__project-manager-mcp__get_task_details - Analyze dependencies and parallel groups
  • mcp__project-manager-mcp__acquire_task_lock - Atomic task locking
  • mcp__project-manager-mcp__update_task_status - Status management
  • mcp__project-manager-mcp__update_task - Progress logging and metadata updates
  • mcp__project-manager-mcp__release_task_lock - Lock management

Epic Orchestration Protocol

1. Epic Discovery and Validation

Step 1: Resolve epic by name
- Use mcp__project-manager-mcp__list_epics to find epic
- If not found, suggest similar epic names
- Validate epic contains tasks ready for execution

Step 2: Task inventory
- Use mcp__project-manager-mcp__list_tasks(epic_id=...) to get all tasks
- Filter out completed tasks
- Identify blocked or in-progress tasks
- Build complete task dependency graph

2. Dependency Analysis and Parallelization Planning

Dependency Graph Construction:
- For each task: mcp__project-manager-mcp__get_task_details(task_id)
- Extract dependencies from ra_metadata.dependencies or dependencies field
- Build directed acyclic graph (DAG) of task dependencies
- Identify parallel groups from parallel_group field
- Detect conflicts from conflicts_with field

Parallelization Strategy:
- Group tasks by dependency level (0=no deps, 1=depends on level 0, etc.)
- Within each level, identify parallel-safe task groups
- Respect parallel_group constraints (tasks in same group can run together)
- Honor conflicts_with restrictions (conflicting tasks cannot run simultaneously)
- Calculate maximum parallel execution streams

Read the full file on GitHub · 338 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. 2d ago First seen · 338 lines · 11 tokens per session scan A f78d1b1fcb76

Subscribe to this mod's changes

epic-run is a command published in the GitHub repository dtannen/pm (0 stars, last pushed 10mo ago), licensed MIT. It adds 11 tokens to every session and 2,490 once invoked, about $0.0001 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.