epic-start

epic-start is a command for Claude Code from kamiazya/scopes. It costs 0 tokens per session (1,560 once invoked), scanned A, original, Apache-2.0.

A command that starts an epic, meaning a large piece of work divided into smaller tasks, by launching several agents in parallel on a shared branch. It checks that the epic, repository sync, branch, and working tree are ready.

In plain words
What is it for?
Use it to verify an epic, create or enter its branch, synchronize it with the repository, and start parallel agents for its tasks.
Why use it?
It organizes parallel work while preventing common setup problems, such as missing synchronization or uncommitted changes. This gives multiple agents a defined branch to work on.

Command for Claude Code

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/kamiazya/scopes/epic-start
Clone the repo
git clone --depth 1 https://github.com/kamiazya/scopes

Made for: Claude Code.

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-start

README.md
[![agentmods](https://agentmods.dev/badge/commands/kamiazya/scopes/epic-start.svg)](https://agentmods.dev/commands/kamiazya/scopes/epic-start)
Your own site
<a href="https://agentmods.dev/commands/kamiazya/scopes/epic-start"><img src="https://agentmods.dev/badge/commands/kamiazya/scopes/epic-start.svg" alt="Measured on agentmods" height="20"></a>
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 1,560 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 $0.01560
Opus 5 $0.00000 $0.00780
Sonnet 5 $0.00000 $0.00312
Haiku 4.5 $0.00000 $0.00156

Measured 3d ago against content hash 78052a15d506, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

epic-start 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 3d 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/commands/pm/epic-start.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Epic Start

Launch parallel agents to work on epic tasks in a shared branch.

Usage

/pm:epic-start <epic_name>

Quick Check

  1. Verify epic exists:

    test -f .claude/epics/$ARGUMENTS/epic.md || echo "❌ Epic not found. Run: /pm:prd-parse $ARGUMENTS"
    
  2. Check GitHub sync: Look for github: field in epic frontmatter. If missing: "❌ Epic not synced. Run: /pm:epic-sync $ARGUMENTS first"

  3. Check for branch:

    git branch -a | grep "epic/$ARGUMENTS"
    
  4. Check for uncommitted changes:

    git status --porcelain
    

    If output is not empty: "❌ You have uncommitted changes. Please commit or stash them before starting an epic"

Instructions

1. Create or Enter Branch

Follow /rules/branch-operations.md:

# Check for uncommitted changes
if [ -n "$(git status --porcelain)" ]; then
  echo "❌ You have uncommitted changes. Please commit or stash them before starting an epic."
  exit 1
fi

# If branch doesn't exist, create it
if ! git branch -a | grep -q "epic/$ARGUMENTS"; then
  git checkout main
  git pull origin main
  git checkout -b epic/$ARGUMENTS
  git push -u origin epic/$ARGUMENTS
  echo "✅ Created branch: epic/$ARGUMENTS"
else
  git checkout epic/$ARGUMENTS
  git pull origin epic/$ARGUMENTS
  echo "✅ Using existing branch: epic/$ARGUMENTS"
fi

2. Identify Ready Issues

Read all task files in .claude/epics/$ARGUMENTS/:

  • Parse frontmatter for status, depends_on, parallel fields
  • Check GitHub issue status if needed
  • Build dependency graph

Categorize issues:

  • Ready: No unmet dependencies, not started
  • Blocked: Has unmet dependencies
  • In Progress: Already being worked on
  • Complete: Finished

3. Analyze Ready Issues

For each ready issue without analysis:

# Check for analysis
if ! test -f .claude/epics/$ARGUMENTS/{issue}-analysis.md; then
  echo "Analyzing issue #{issue}..."
  # Run analysis (inline or via Task tool)
fi

Read the full file on GitHub · 248 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. 3d ago First seen · 248 lines · 0 tokens per session scan A 78052a15d506

Subscribe to this mod's changes

epic-start is a command published in the GitHub repository kamiazya/scopes (2 stars, last pushed 9mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,560 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.