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-approvegit 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-approve)<a href="https://agentmods.dev/commands/seanrreid/rad_framework/rad-approve"><img src="https://agentmods.dev/badge/commands/seanrreid/rad_framework/rad-approve.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 | $0.00082 | $0.03107 |
| Opus 5 | $0.00041 | $0.01554 |
| Sonnet 5 | $0.00016 | $0.00621 |
| Haiku 4.5 | $0.00008 | $0.00311 |
Grade A, and why
rad-approve 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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/rad-approve
Review a pending plan and approve it for execution. Under the Lane B model the
plan doc lives on its rad/[feature] work branch; approval is recorded on that
branch tip. Nothing is committed to the default branch here.
Input
$ARGUMENTS should be a plan name or path, optionally followed by the
proxy-approval flags:
feature-name→ resolves to.agents/plans/feature-name.mdonrad/feature-name.agents/plans/feature-name.md→ used directlyfeature-name --on-behalf-of "Sean R Reid" --evidence "Slack #rad 2026-05-28: 'plan looks good, approve it'"
Proxy approval (--on-behalf-of)
By default this command is architect-only — it gates on the git user's role.
When the architect approves a plan out-of-band (Slack, a PR comment, a verbal
yes in standup) but doesn't run /rad-approve themselves, a team member may
record that approval with:
--on-behalf-of "<architect name>"— who actually approved. Must resolve to a configured architect in CLAUDE.md (validated, not just typed).--evidence "<text or link>"— required with--on-behalf-of. A quote, Slack permalink, or PR-comment URL showing the architect's approval. This is the audit-trail substitute for the architect running the command themselves.
The recording user's own git identity is captured separately as Recorded-By,
so the record always shows both who approved and who entered it.
If empty, list plans awaiting approval (reading branch tips, since plans live on their work branches):
scripts/rad-status.sh 2>/dev/null | grep pending-review \
|| echo "No pending plans found."
Process
Step 1: Verify authority to approve
First, parse $ARGUMENTS for the proxy flags. Everything before the first --
flag is the plan name/path; capture the values of --on-behalf-of and
--evidence if present.
Default (no --on-behalf-of) — gate on the running user's role:
scripts/check-role.sh architect
If the script exits non-zero, stop. Do not proceed.
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 · 348 lines · 82 tokens per session scan A 16a132e09980
rad-approve is a command published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 3,107 once invoked, about $0.0004 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.