RAD_framework: Command for Claude Code

.claude/commands/team/rad-adopt.md

rad-adopt is a command for Claude Code from seanrreid/RAD_framework. It costs 59 tokens per session (3,638 once invoked), scanned A, original, MIT.

A command that turns an existing GitHub or GitLab issue, or a written problem description, into a structured RAD work plan. RAD is a development workflow that plans work in waves and requires approval before execution.

In plain words
What is it for?
Use it with an issue URL, issue number, or free-form description to create a plan file. The plan can then be reviewed through /rad-approve before implementation.
Why use it?
It brings older work into the same planning and approval process as newer tasks. It also gathers the issue details and codebase context so the plan has enough information to review.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions subagents; mentions Claude Code.

This is seanrreid/RAD_framework's own configuration. It tells Claude Code how to work on RAD_framework itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything RAD_framework configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node harness/cli.js config get roles.developers # also roles.designers, roles.architect.

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/seanrreid/RAD_framework/main/.claude/commands/team/rad-adopt.md
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-adopt

README.md
[![agentmods](https://agentmods.dev/badge/commands/seanrreid/rad_framework/rad-adopt/github.svg)](https://agentmods.dev/commands/seanrreid/rad_framework/rad-adopt)
Your own site
<a href="https://agentmods.dev/commands/seanrreid/rad_framework/rad-adopt"><img src="https://agentmods.dev/badge/commands/seanrreid/rad_framework/rad-adopt/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 rad-adopt

Your own site · 80×15
<a href="https://agentmods.dev/commands/seanrreid/rad_framework/rad-adopt"><img src="https://agentmods.dev/badge/commands/seanrreid/rad_framework/rad-adopt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,638 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 $0.00059 $0.03638
Opus 5.5 $0.00024 $0.01455
Sonnet 5.5 $0.00012 $0.00728
Haiku 4.5 $0.00006 $0.00364

Measured 16d ago against content hash a960c18a9cb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rad-adopt 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 16d 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/team/rad-adopt.md · 363 lines

How it starts

The opening of the file, as written. The whole thing — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rad-adopt

Convert a pre-existing issue into a RAD plan. Use this for work that existed before the RAD framework was introduced.

Input

The input ($ARGUMENTS) can be:

  • A GitHub/GitLab issue URL: https://github.com/org/repo/issues/42
  • An issue number: #42 or 42
  • A free-form description: "Fix the login timeout not resetting on activity"

If empty, ask for the issue reference or description before proceeding.

--override-disposition "<reason>" may accompany the input to proceed past a research artifact's cited non-actionable disposition (see Step 2b). The override and its reason are recorded in the plan header.

--playbook <kind>/<slug>[@<version>] may accompany the input to start from a pinned playbook in .agents/playbooks/ (see Step 3b). A bare ref pins the playbook's current version.


Process

Step 1: Determine role and available agents

Read the role and scope config from .rad/config.yml (see docs/configuration.md):

node harness/cli.js config get roles.developers   # also roles.designers, roles.architect
node harness/cli.js config get agent_scope_map    # one { agent, type, reads, roles } row per line

From that output, find:

  • The current user's role (architect, developer, or designer)
  • Which agents are available for this role (rows whose roles include it)

Only call agents available to your role. Flag out-of-scope dependencies in the plan rather than working around them.

Step 2: Fetch issue context

If $ARGUMENTS is a URL or issue number:

# GitHub
gh issue view [number-or-url] --json title,body,labels,comments,assignees,url

# GitLab
glab issue view [number-or-url] --output json

Extract:

  • Title
  • Body / description
  • Labels
  • Comments (summarize if long — keep to ≤10 lines)
  • Issue URL (for Adopted-From: field)

If the CLI is unavailable or the fetch fails, prompt the user to paste the issue content directly and use that as the description.

Read the full file on GitHub · 363 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. 16d ago Changed · +4 lines a960c18a9cb0
  2. 17d ago Changed · +3 lines 6e36ddbdaf6d
  3. 20d ago Changed · +48 lines f6fd6be1f1cf
  4. 22d ago Changed · +6 lines · -2 tokens per session 85e3b3c373bc
  5. 27d ago Changed · +6 lines d881ca489de5
  6. 29d ago Changed · +28 lines c390fe8c1eb1
  7. 1mo ago Changed · +12 lines 674f1d8b2c91
  8. 1mo ago Changed · +8 lines f0ced9bb10d4
  9. 1mo ago Changed · +5 lines f33dc12ef9f5
  10. 2mo ago First seen · 243 lines · 61 tokens per session scan A bb20cd60db6a

Subscribe to this mod's changes

rad-adopt is a command published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 4d ago), licensed MIT. It adds 59 tokens to every session and 3,638 once invoked, about $0.0002 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 2026-08-31.