build-epic

build-epic is a command for Claude Code from shashankreddy509/claude-tdd-kit. It costs 0 tokens per session (2,492 once invoked), scanned A, original, MIT.

A read-only planning command that lists open tickets in a Jira epic in board order and marks each as ready to build, blocked, or waiting on an owner.

In plain words
What is it for?
Use it to assess a Jira epic before implementation and identify tickets that need clarification or another person's action.
Why use it?
It shows what can be worked on now and in what order without creating branches, worktrees, plans, or code changes.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the tdd-pipeline plugin — 7 commands, 13 agents shipped together

Good fit Use it to assess a Jira epic before implementation and identify tickets that need clarification or another person's action.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add shashankreddy509/claude-tdd-kit
Claude Code
/plugin install tdd-pipeline

Made for: Claude Code.

Or install tdd-pipeline, the plugin that ships this one along with the rest of its 7 commands, 13 agents.

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 build-epic

README.md
[![agentmods](https://agentmods.dev/badge/commands/shashankreddy509/claude-tdd-kit/build-epic/github.svg)](https://agentmods.dev/commands/shashankreddy509/claude-tdd-kit/build-epic)
Your own site
<a href="https://agentmods.dev/commands/shashankreddy509/claude-tdd-kit/build-epic"><img src="https://agentmods.dev/badge/commands/shashankreddy509/claude-tdd-kit/build-epic/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for build-epic

Your own site · 80×15
<a href="https://agentmods.dev/commands/shashankreddy509/claude-tdd-kit/build-epic"><img src="https://agentmods.dev/badge/commands/shashankreddy509/claude-tdd-kit/build-epic.svg" alt="Reviewed on agentmods" width="80" 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 2,492 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.02492
Opus 5.5 $0.00000 $0.00997
Sonnet 5.5 $0.00000 $0.00498
Haiku 4.5 $0.00000 $0.00249

Measured 5d ago against content hash 91ea4bdc7980, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

build-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 5d 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.

tdd-pipeline/commands/build-epic.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

List an epic's open tickets in board order and tag each one buildable, blocked or owner-step, so you know which tickets can be built now and in what order. Steps 1-3 only read Jira and git and print the list. Step 4 builds the buildable tickets one at a time, only when the user says yes.

Triggers: /tdd-pipeline:build-epic <EPIC-KEY>, e.g. /tdd-pipeline:build-epic PROJ-70.

Epic: $ARGUMENTS


Step 0 — Preconditions

  • No key in $ARGUMENTS → STOP: "Name the epic: /tdd-pipeline:build-epic <EPIC-KEY>."
  • Run the Wiring check and Detection in ${CLAUDE_PLUGIN_ROOT}/references/jira-mcp.md. This command is entirely about the ticket: no Jira: line, or no Atlassian MCP → STOP with that file's one line.
  • Determine <default> per ${CLAUDE_PLUGIN_ROOT}/references/git-host.md, then git fetch origin <default> -q.
  • Worktree check: a JS repo (package.json at the root) or an iOS repo (Podfile or a *.xcodeproj) with no .worktreeinclude at the root → STOP. Test each marker on its own ([ -e package.json ], [ -e Podfile ], find . -maxdepth 1 -name '*.xcodeproj'): one ls with a glob aborts in zsh when the glob matches nothing. "❌ No .worktreeinclude: a worktree of this repo starts without its gitignored files (.env, node_modules, Pods). List the ones a build needs in .worktreeinclude, then re-run."

Step 1 — Read the epic's open children

One call to the resolved search issues by JQL tool:

parent = <EPIC> AND statusCategory != Done ORDER BY rank ASC

Ask for fields summary, status, issuetype, issuelinks, description (50 results; description feeds rule 4), in the tool's fuller view when its schema has one (see ${CLAUDE_PLUGIN_ROOT}/references/jira-mcp.md). If issuelinks is still missing from every row, print once: "⚠️ Jira returned no issuelinks: blockers come from titles only." Never read a missing field as "no blockers". One plain line each, then STOP:

  • the key does not exist or is not an epic → "❌ is not an epic."
  • zero rows → "✅ has no open children."
  • the call fails → "⚠️ Jira unreachable: ."

Read the full file on GitHub · 142 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. 5d ago Changed · +6 lines 91ea4bdc7980
  2. 9d ago Changed · +39 lines 53830c9d0fdc
  3. 10d ago First seen · 97 lines · 0 tokens per session scan A 4add317a5c3c

Subscribe to this mod's changes

build-epic is a command published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,492 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 2026-10-16.