epic-tasks

A command that breaks a large technical feature, called an epic, into smaller implementation tasks with plans and dependencies. Dependencies show which tasks must be completed first.

In plain words
What is it for?
Checking an epic, creating detailed tasks, adding acceptance criteria and file lists, recording planning details, and setting dependencies and parallel-work metadata.
Why use it?
It turns broad work into trackable tasks and records the information agents need to coordinate parallel work safely.

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-tasks
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.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,771 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 $0.00013 $0.03771
Opus 5 $0.00006 $0.01886
Sonnet 5 $0.00003 $0.00754
Haiku 4.5 $0.00001 $0.00377

Measured 2d ago against content hash e2b0e08b808d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

epic-tasks 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-tasks.md · 425 lines

How it starts

The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Break Epic into Granular Tasks

Transform a technical epic into specific, actionable tasks with detailed implementation plans.

Usage

/pm:epic-tasks <feature-name>

Instructions

You are breaking down the epic for: $ARGUMENTS

MCP Integration (preferred)

Use MCP to validate epic context and create tasks with structured metadata.

  • Full name: mcp__project-manager-mcp__list_epics
  • Full name: mcp__project-manager-mcp__list_tasks
  • Full name: mcp__project-manager-mcp__create_task
  • Full name: mcp__project-manager-mcp__update_task

Recommended flow:

  1. Validate epic exists by name via mcp__project-manager-mcp__list_epics (or by id if known).
  2. For each granular task, create it with mcp__project-manager-mcp__create_task using epic_name=$ARGUMENTS and initial ra_metadata (acceptance criteria, file list, dependencies) plus parallel execution fields: parallel_group, conflicts_with, and parallel_eligible.
  3. For RA planning blocks, persist planning details in ra_metadata.planning via mcp__project-manager-mcp__update_task.
  4. CRITICAL: Include proper dependencies field (task ID array) and parallel execution metadata to enable agent coordination.
  5. Optionally mirror task files into .pm/tasks/ for local context; MCP remains the source of truth.

1. Validate Epic Exists

  • Prefer MCP: verify via mcp__project-manager-mcp__list_epics by name; error if not found.
  • Optionally read .pm/epics/$ARGUMENTS.md for additional context.

2. Task Breakdown Philosophy

CRITICAL: No Vague Tasks Allowed

Every task must be:

  • 2-8 hours maximum (no exceptions)
  • Concrete and specific (exact files, functions, components to build)
  • Independently executable (minimal dependencies)
  • Clearly testable (specific success criteria)
  • One logical unit of work (single feature/component/endpoint)

Bad Task Examples (DON'T DO THIS):

  • ❌ "Implement user management"
  • ❌ "Add authentication"
  • ❌ "Create API endpoints"
  • ❌ "Build frontend"

Read the full file on GitHub · 425 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 · 425 lines · 13 tokens per session scan A e2b0e08b808d

Subscribe to this mod's changes

epic-tasks is a command published in the GitHub repository dtannen/pm (0 stars, last pushed 10mo ago), licensed MIT. It adds 13 tokens to every session and 3,771 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.