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 commands/dtannen/pm/epic-rungit clone --depth 1 https://github.com/dtannen/pmWrote 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/commands/dtannen/pm/epic-run)<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>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 | $0.00011 | $0.02490 |
| Opus 5 | $0.00005 | $0.01245 |
| Sonnet 5 | $0.00002 | $0.00498 |
| Haiku 4.5 | $0.00001 | $0.00249 |
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.
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 namemcp__project-manager-mcp__list_tasks- Get all tasks in epicmcp__project-manager-mcp__get_task_details- Analyze dependencies and parallel groupsmcp__project-manager-mcp__acquire_task_lock- Atomic task lockingmcp__project-manager-mcp__update_task_status- Status managementmcp__project-manager-mcp__update_task- Progress logging and metadata updatesmcp__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
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.
- 2d ago First seen · 338 lines · 11 tokens per session scan A f78d1b1fcb76
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.