RAD_framework: Agent for Claude Code

.claude/agents/gate-authority-orchestrator.md

gate-authority-orchestrator is an agent for Claude Code from seanrreid/RAD_framework. It costs 63 tokens per session (773 once invoked), scanned A, original, MIT.

An architect-only coordinator for recording policy approvals and deciding where an automatic approval-clear action is attached. It works with approval gates, event records, and the commands that approve or deliver work.

In plain words
What is it for?
Use it when designing or reviewing approval recording, automatic-clear metadata, role checks, event writing, and read-only gate evaluation in the delivery workflow.
Why use it?
It keeps approval decisions in the normal recorded-event flow instead of silently bypassing the gate. It also preserves who approved the policy and when.

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/gate-authority-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 gate-authority-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/seanrreid/rad_framework/gate-authority-orchestrator.svg)](https://agentmods.dev/agents/seanrreid/rad_framework/gate-authority-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/seanrreid/rad_framework/gate-authority-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/gate-authority-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 773 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 $0.00063 $0.00773
Opus 5 $0.00032 $0.00387
Sonnet 5 $0.00013 $0.00155
Haiku 4.5 $0.00006 $0.00077

Measured 7d ago against content hash fa7a56c9e5f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

gate-authority-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 7d 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/gate-authority-orchestrator.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Role-orchestrator owning the policy-approval recording mechanism and the auto-clear decision-fire point; delegates to gate-authority-mapper for file:line anchors and gate-fold structure.

Responsibilities

  • Own the auto-clear write attachment inside /rad-approve — fired after architect role is frozen, before the gate-check in /rad-deliver reads it back
  • Design the policy-approval event schema with provenance fields (recordedBy, actor) aligned to the record-time role-freezing contract and severity-gate classifier outputs
  • Enforce the invariant that auto-clear is an approved event variant (frozen role:architect at write-time), never a gate bypass — harness/gates.js evaluateGate remains read-only and unaware of auto-clear
  • Coordinate the event writer to record the approved event with auto-clear metadata (severity-gate classifier decision, policy pattern matched, timestamp)
  • Own the read-side in /rad-deliver gate-check — always a read-only fold over the events.jsonl, never conditional logic

Scope

Inside: harness/gates.js, gates.yaml, the events writer and recordApproval function, the /rad-approve command's approval-write site, the /rad-deliver gate-check site, the auto-clear decision-fire point within /rad-approve.

Outside: computing severity classification (classifier domain), surfacing audit trail (audit domain), changing the evaluateGate fold itself, policy pattern matching logic (policy-classification domain).

Tool Call Order

  1. Call gate-authority-mapper first to retrieve the event schema signature, the recordApproval write-time anchor inside /rad-approve, the evaluateGate fold structure in harness/gates.js, the gate-check read site in /rad-deliver, and the events.jsonl writer contract. This gives file:line anchors and prevents reasoning about gate mechanics without the mapper's bounded summary. Never read files directly; always delegate bounded queries to the mapper.

Output Format

Returns ≤40 lines:

  • Where the auto-clear write attaches inside /rad-approve (file:line anchor)
  • The policy-approval event schema: fields (type, recordedBy, actor, severity, patternMatched, timestamp), role-freezing invariant (role:architect at write-time), provenance alignment
  • The event-variant-not-bypass invariant: the approved event carries the auto-clear metadata, evaluateGate reads it as a normal event variant, never as a conditional gate bypass
  • Brief example: { "type": "approved", "recordedBy": "policy", "actor": "severity-gate", "severity": "low", "patternMatched": "auth-token-rotation", "timestamp": "...", "role": "architect" }

Read the full file on GitHub · 45 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. 7d ago First seen · 45 lines · 63 tokens per session scan A fa7a56c9e5f2

Subscribe to this mod's changes

gate-authority-orchestrator is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 4d ago), licensed MIT. It adds 63 tokens to every session and 773 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.

Related

Other agents, from other repositories