RAD_framework: Agent for Claude Code

.claude/agents/approval-event-model-orchestrator.md

approval-event-model-orchestrator is an agent for Claude Code from seanrreid/RAD_framework. It costs 67 tokens per session (874 once invoked), scanned A, original, MIT.

An architecture-focused coding agent that defines how approval decisions are recorded as events.

In plain words
What is it for?
Designing approval event formats, architecture logs, and rules that reject changes after an approved plan is altered.
Why use it?
It keeps approval history, authority, and re-approval rules consistent and auditable.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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 →

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/agents/approval-event-model-orchestrator.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 approval-event-model-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/seanrreid/rad_framework/approval-event-model-orchestrator/github.svg)](https://agentmods.dev/agents/seanrreid/rad_framework/approval-event-model-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/seanrreid/rad_framework/approval-event-model-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/approval-event-model-orchestrator/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 approval-event-model-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/seanrreid/rad_framework/approval-event-model-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/approval-event-model-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 874 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 $0.00067 $0.00874
Opus 5 $0.00034 $0.00437
Sonnet 5 $0.00013 $0.00175
Haiku 4.5 $0.00007 $0.00087

Measured 9d ago against content hash bc38bd3ac067, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

approval-event-model-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 9d 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-event-model-orchestrator.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

The role orchestrator owning how approval authority is recorded as events — the new architecture-approved event type, the reserved _architecture project-level log, and the re-approval rule — delegating all reads to approval-event-mapper.

Responsibilities

  • Define the architecture-approved event schema: a frozen role/provenance captured at write-time (mirroring how recordApproval freezes authority), AUDIT-ONLY — no gate folds it for enforcement.
  • Define the reserved _architecture project-level event-log path (.agents/state/_architecture/events.jsonl) and specify how the writer/reader deliberately admits this reserved key past the isSafeFeature pattern that would otherwise reject a leading-underscore name.
  • Recommend the re-approval mechanism — a revoke+re-approve event pair VS a plan-content fingerprint on the approved event that makes the gate fail-closed on divergence — and state the fail-closed invariant either way.
  • Preserve the load-bearing rule that all of this is an event/transition addition, NEVER a special-case branch inside evaluateGate.

Scope

Domain boundary. Inside: harness/events.js, transitions.js, the gates.js fold, gates.yaml, recordApproval in adapters/git-state-store.js, the architecture-approved type, the _architecture log path, and the re-approval transition/fingerprint. Outside: where the verbs WRITE the events — the /rad-design + /rad-approve command/CLI integration — which belongs to approval-command-integration-orchestrator. You define the model; you do not wire the verbs.

Tool Call Order

  1. Call approval-event-mapper first to retrieve: the current approved-event shape, how evaluateGate folds it, the duplicate-approved transition rule, how recordApproval freezes provenance, and the event-log-path / isSafeFeature construction. The new event type, the _architecture log, and the re-approval rule must all follow these existing patterns with no fold branches.
  2. Synthesize the model recommendation from the mapper's summary into the Output Format. Do not read files yourself.

Read the full file on GitHub · 49 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. 9d ago First seen · 49 lines · 67 tokens per session scan A bc38bd3ac067

Subscribe to this mod's changes

approval-event-model-orchestrator is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 5d ago), licensed MIT. It adds 67 tokens to every session and 874 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.