rad-epic-decompose

rad-epic-decompose is a command for Claude Code from seanrreid/RAD_framework. It costs 107 tokens per session (1,896 once invoked), scanned A, original, MIT.

An architect-only command that reads a GitHub epic and its child issues, then writes a draft document breaking the epic into smaller shaping stories. An epic is a large piece of planned work made up of related issues.

In plain words
What is it for?
Use it at the first shaping stage of a project to inspect an epic, summarize each child story, create an epic-level overview, and prepare an architect sign-off checklist.
Why use it?
It turns a broad issue into a structured view of the work before detailed research or implementation planning begins. It also checks that the current user has the architect role.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions CLAUDE.md.

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/seanrreid/rad_framework/rad-epic-decompose
Clone the repo
git clone --depth 1 https://github.com/seanrreid/RAD_framework

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 rad-epic-decompose

README.md
[![agentmods](https://agentmods.dev/badge/commands/seanrreid/rad_framework/rad-epic-decompose.svg)](https://agentmods.dev/commands/seanrreid/rad_framework/rad-epic-decompose)
Your own site
<a href="https://agentmods.dev/commands/seanrreid/rad_framework/rad-epic-decompose"><img src="https://agentmods.dev/badge/commands/seanrreid/rad_framework/rad-epic-decompose.svg" alt="Measured on agentmods" height="20"></a>
Per session 107 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,896 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 5.1 $0.00107 $0.01896
Opus 5 $0.00053 $0.00948
Sonnet 5 $0.00021 $0.00379
Haiku 4.5 $0.00011 $0.00190

Measured 5d ago against content hash 89d8d18d4351, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

rad-epic-decompose 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.

.claude/commands/architect/rad-epic-decompose.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/rad-epic-decompose

Consume a GitHub epic issue and produce a per-child decomposition artifact the architect uses to shape the epic into deliverable work. This sits upstream of the RAD workflow at Gate 0: it shapes; it does not plan, research, or deliver.

The output is a discovery/shaping document — a structured read on each child story plus an epic-level rollup with an architect sign-off checklist. It is written but never auto-committed, never turned into plan files, and never flips any status.

Input

$ARGUMENTS is the epic issue number or URL. Examples: 42, #42, https://github.com/org/repo/issues/42.

If $ARGUMENTS is empty, stop:

✗ /rad-epic-decompose requires an epic issue number or URL.
  Usage: /rad-epic-decompose <issue-number-or-url>

Process

Step 1: Verify authority to decompose

This command is architect-only. Gate on the running user's role before any fetch or context read:

scripts/check-role.sh architect

If the script exits non-zero, stop. Do not fetch the epic, do not read context, do not write anything.

Step 2: Fetch the epic and its children

Only after the role gate passes, call the Wave 1 fetch script with the raw $ARGUMENTS value. The script normalizes a bare number, #NN, or a GitHub issue URL itself, so pass the argument through unchanged:

scripts/fetch-epic.sh "$ARGUMENTS"

The script emits a single JSON object on stdout:

{ "epic": { "number": …, "title": …, "body": …, "url": …, "milestone": …, "labels": […], "state": … },
  "children": [ { "number": …, "title": …, "body": …, "url": …, "milestone": …, "labels": […], "state": … }, … ] }

It is GitHub-only for v1 and exits non-zero with a clear message on any other platform or if gh/jq are missing (set RAD_PLATFORM only when testing). If the script exits non-zero, surface its message and stop — do not fabricate epic or child data.

Capture the epic number N and derive a kebab-case slug from the epic title (lowercase, spaces and punctuation collapsed to single hyphens, no leading or trailing hyphen).

Read the full file on GitHub · 210 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 First seen · 210 lines · 107 tokens per session scan A 89d8d18d4351

Subscribe to this mod's changes

rad-epic-decompose is a command published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 2d ago), licensed MIT. It adds 107 tokens to every session and 1,896 once invoked, about $0.0005 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.