plan-epic

A command that creates a GitHub Project from a planning document and connects its work items to GitHub issues. It can also link existing issues to an existing project.

In plain words
What is it for?
Use it to turn an epic or planning document into a project board, find or create matching issues, assign phases and priorities, and link issues to the board.
Why use it?
It removes repetitive project setup and issue-linking work when a plan already describes the work. It organizes the result with Priority, Phase, and Status fields.

Command

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/anettodev/github-planner/plan-epic
Clone the repo
git clone --depth 1 https://github.com/anettodev/github-planner
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 891 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 $0.00000 $0.00891
Opus 5 $0.00000 $0.00445
Sonnet 5 $0.00000 $0.00178
Haiku 4.5 $0.00000 $0.00089

Measured yesterday against content hash 3d71b76a0aa4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-epic 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.

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.

src/commands/plan-epic.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Epic from Planning Document

Create a GitHub Project (v2) from a planning document, link issues, and configure custom fields (Priority, Phase, Status).

Arguments: $ARGUMENTS (required — path to planning document OR --link-only #1 #2 #3, optional flags: --repo owner/repo, --project-number N)

Steps

1. Parse Arguments

  • If --link-only is present, skip document parsing (step 3). Collect issue numbers from arguments.
  • If --project-number N is present, link to an existing project instead of creating a new one.
  • Otherwise, the first argument is the path to the planning document.

2. Detect Repository

  • If --repo flag provided, use that
  • Otherwise run gh repo view --json nameWithOwner -q .nameWithOwner
  • Confirm with user before proceeding: "Will create project in owner/repo. Continue?"

3. Extract Epic Structure

Use the epic-to-project skill to parse the document:

  • Extract project title and description
  • Identify phases → custom field options
  • Identify priority levels for each item
  • Determine which items map to existing issues vs. need creation

4. Resolve Issues

For each item in the epic:

  • Search for existing issues: gh issue list --search "KEY_WORDS" --state open --limit 5 --json number,title
  • If a match exists, use that issue number
  • If no match, flag as "needs creation"

For --link-only mode, verify each issue number exists:

gh issue view N --json number,title,labels,milestone

Map existing labels and milestones to field values.

5. Check for Existing Project

If --project-number is provided, verify it exists. Otherwise:

gh project list --owner OWNER --format json

If a project with the same title exists, ask: "Project 'TITLE' already exists (#N). Use it or create new?"

6. Present Plan for Approval

Show the full plan before creating anything:

Will create project "Epic: Auth Overhaul" in owner/repo:

Custom fields:
  - Priority: Critical, High, Medium, Low
  - Phase: Phase 1, Phase 2, Phase 3
  - Status: Todo, In Progress, In Review, Done

Milestones:
  - Phase 1 → reuse existing #2
  - Phase 2 → create new
  - Phase 3 → create new

| # | Issue | Title                    | Priority | Phase   | Milestone | Status |
|---|-------|--------------------------|----------|---------|-----------|--------|
| 1 | #45   | Remove dead files        | Critical | Phase 1 | Phase 1   | Todo   |
| 2 | #46   | Update Project.swift     | High     | Phase 2 | Phase 2   | Todo   |
| 3 | NEW   | Add caching layer        | Medium   | Phase 3 | Phase 3   | Todo   |

Issues to create first: 1
Issues to link: 2
Milestones to create: 2 · to reuse: 1

Proceed? (yes/no)

Read the full file on GitHub · 110 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. yesterday First seen · 110 lines · 0 tokens per session scan A 3d71b76a0aa4

Subscribe to this mod's changes

plan-epic is a command published in the GitHub repository anettodev/github-planner (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 891 tokens. 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.