RAD_framework: Command for Claude Code

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

rad-review is a command for Claude Code from seanrreid/RAD_framework. It costs 54 tokens per session (4,238 once invoked), scanned A, original, MIT.

A command that checks changes on a rad/ work branch against its plan and the project's conventions. It also checks whether changed files stay within the planned scope and whether tests cover the acceptance criteria.

In plain words
What is it for?
Use it after implementation and before requesting review, either for the whole branch or for specific files.
Why use it?
It catches work that drifted beyond the plan, violates project rules, or lacks required tests before an architect reviews the proposed changes.

Command for Claude Code

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

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 digest "$FEATURE".

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-review.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-review

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/seanrreid/rad_framework/rad-review"><img src="https://agentmods.dev/badge/commands/seanrreid/rad_framework/rad-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,238 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 $0.00054 $0.04238
Opus 5.5 $0.00022 $0.01695
Sonnet 5.5 $0.00011 $0.00848
Haiku 4.5 $0.00005 $0.00424

Measured 8d ago against content hash 4fd977b7546c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rad-review 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 8d 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-review.md · 405 lines

How it starts

The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/rad-review

Self-review the rad/[feature] work branch before requesting architect review. Catches problems early — better to find them now than in the architect's review of the deliver PR.

Input

$ARGUMENTS (optional): specific files to review. If empty, reviews all changes on the current rad/[feature] branch since it diverged from the default branch.

BASE=$(scripts/get-default-branch.sh)
git diff "$BASE"...HEAD --name-only

Process

Step 1: Load context

  • Read AGENTS.md for project conventions and constraints (or CLAUDE.md if the project has no AGENTS.md)
  • Read the plan file for this work branch:
    BASE=$(scripts/get-default-branch.sh)
    FEATURE=$(git branch --show-current | sed 's#^rad/##')
    PLAN=".agents/plans/$FEATURE.md"
    
  • Read the execution log:
    LOG=$(ls .agents/logs/$FEATURE-*.md 2>/dev/null | tail -1)
    

Step 1b: Review digest

node harness/cli.js digest "$FEATURE"

Run the read-only review digest and include its full output verbatim in the report's ### Digest section. It ranks where to look first (scope violations, approval not intact, un-waived then waived high-risk paths, self-protected paths, deficit forecast, finding recurrence, run evidence) and shows unavailable inputs explicitly. The digest is advisory only — it informs the review and never changes its pass/fail by itself.

If it exits non-zero (2 = usage error or unreadable plan, 1 = malformed event log), record the exit code and its stderr in the ### Digest section and continue the review — a digest failure is reported, never a stop.

Step 2: Scope check

scripts/check-scope.sh "$PLAN" "rad/$FEATURE" "$BASE"

The script outputs each changed file as in-scope or out-of-scope. Include its full output in the review report. Any out-of-scope files are HIGH priority.

Step 2b: Lint advisories

scripts/lint-plan.sh "$PLAN"

Run the plan linter against the plan under review and include its full output in the review report. These are advisory only — they surface plan-quality warnings for the architect's attention but do not gate the review or block architect review. This is separate from the Step 2 scope check.

Read the full file on GitHub · 405 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. 8d ago Changed · +29 lines 4fd977b7546c
  2. 20d ago Changed · +39 lines 95debfa13735
  3. 23d ago Changed · +1 lines 1732f020916d
  4. 29d ago Changed · +60 lines 8a09c5f3d51f
  5. 1mo ago Changed · +8 lines c76d442873bc
  6. 1mo ago Changed · +12 lines c8bf9179f9ce
  7. 2mo ago First seen · 256 lines · 54 tokens per session scan A 9690ffae928f

Subscribe to this mod's changes

rad-review is a command published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 4d ago), licensed MIT. It adds 54 tokens to every session and 4,238 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.