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.
npx agentmods add commands/seanrreid/rad_framework/rad-epic-decomposegit 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/commands/seanrreid/rad_framework/rad-epic-decompose)<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>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 | $0.00107 | $0.01896 |
| Opus 5 | $0.00053 | $0.00948 |
| Sonnet 5 | $0.00021 | $0.00379 |
| Haiku 4.5 | $0.00011 | $0.00190 |
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.
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).
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.
- 5d ago First seen · 210 lines · 107 tokens per session scan A 89d8d18d4351
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.