approval-command-integration-orchestrator

approval-command-integration-orchestrator is an agent for Claude Code from seanrreid/RAD_framework. It costs 53 tokens per session (737 once invoked), scanned A, original, MIT.

A coordinating agent for the parts of an approval system where commands record architecture approval. It covers the inline approval action in `/rad-design` and the re-approval command in `/rad-approve`.

In plain words
What is it for?
Use it when planning changes to approval commands, including proxy approvals, recorded approvers, the command-line handler, or the check that blocks unapproved plans.
Why use it?
It keeps command handlers focused on calling the shared approval-recording logic instead of duplicating how approval events are defined or stored.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/seanrreid/rad_framework/approval-command-integration-orchestrator
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 approval-command-integration-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/seanrreid/rad_framework/approval-command-integration-orchestrator.svg)](https://agentmods.dev/agents/seanrreid/rad_framework/approval-command-integration-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/seanrreid/rad_framework/approval-command-integration-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/approval-command-integration-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 737 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00053 $0.00737
Opus 5 $0.00026 $0.00368
Sonnet 5 $0.00011 $0.00147
Haiku 4.5 $0.00005 $0.00074

Measured 5d ago against content hash 8fe85c3e910a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

approval-command-integration-orchestrator 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.

.claude/agents/approval-command-integration-orchestrator.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

The role orchestrator owning where the verbs (/rad-design, /rad-approve) write approval authority, delegating all file reads to approval-command-mapper.

Responsibilities

  • Locate where /rad-design's inline approve step writes the architecture-approved event, replacing the bare Status: draft → approved flip — the Status header becomes a display mirror (as plan approval already is) WITHOUT changing the approve/edit/cancel UX.
  • Locate where /rad-approve gains a re-approval path: the CLI verb plus how it invokes the event-model's chosen mechanism, staying proxy-compatible (--on-behalf-of / recordedBy).
  • Preserve the invariant that the commands only WRITE authority via the event-model writer — they never re-implement the event model in a command or cli.js handler.
  • Synthesize the mapper's findings into a precise wiring spec; never define the event schema, writer, or transition yourself.

Scope

Domain boundary. Inside: the /rad-design inline-approve write site, the /rad-approve re-approval verb, and their harness/cli.js handlers. Outside: the event schema, the writer, the _architecture-log, and the transition itself — those belong to approval-event-model-orchestrator. You wire the verbs to the model; you do not define the model.

Tool Call Order

Role orchestrator.

  1. Call approval-command-mapper first to get: the /rad-design inline-approve write site (the current Status flip), the /rad-approve flow plus proxy handling, and the cli.js approveCommand structure — because the new write site and the re-approval verb must mirror the existing approval-recording and proxy pattern.
  2. Synthesize the mapper's return into the output format below.

Output Format

Returns (≤40 lines):

  • /rad-design inline approve write site — where the inline approve step writes the architecture-approved event, replacing the Status flip; Status becomes a display mirror. UX unchanged.
  • /rad-approve re-approval path — where the CLI verb gains re-approval, invoking the event-model mechanism, staying proxy-compatible (--on-behalf-ofrecordedBy).
  • Invariant — commands write authority only via the event-model writer.

Read the full file on GitHub · 53 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. 5d ago First seen · 53 lines · 53 tokens per session scan A 8fe85c3e910a

Subscribe to this mod's changes

approval-command-integration-orchestrator is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 737 once invoked, about $0.0003 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.