Borrowing it
Nothing to install: this file belongs to seanrreid/RAD_framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/seanrreid/RAD_framework/main/.agents/skills/rad-epic-decompose/SKILL.mdgit clone --depth 1 https://github.com/seanrreid/RAD_frameworkWrote 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/skills/seanrreid/rad_framework/rad-epic-decompose)<a href="https://agentmods.dev/skills/seanrreid/rad_framework/rad-epic-decompose"><img src="https://agentmods.dev/badge/skills/seanrreid/rad_framework/rad-epic-decompose/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.
<a href="https://agentmods.dev/skills/seanrreid/rad_framework/rad-epic-decompose"><img src="https://agentmods.dev/badge/skills/seanrreid/rad_framework/rad-epic-decompose.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00114 | $0.01977 |
| Opus 5.5 | $0.00046 | $0.00791 |
| Sonnet 5.5 | $0.00023 | $0.00395 |
| Haiku 4.5 | $0.00011 | $0.00198 |
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 21d 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 — 207 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
the text the user wrote after the skill name is the epic issue number or URL. Examples: 42, #42,
https://github.com/org/repo/issues/42.
If the text the user wrote after the skill name 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
the text the user wrote after the skill name value. The script normalizes a bare number, #NN, or a GitHub issue
URL itself, so pass the argument through unchanged:
scripts/fetch-epic.sh "the text the user wrote after the skill name"
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.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 21d ago First seen · 207 lines · 114 tokens per session scan A 578e67c18b11
rad-epic-decompose is a skill published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 4d ago), licensed MIT. It adds 114 tokens to every session and 1,977 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-09.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.