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.
curl -O https://raw.githubusercontent.com/seanrreid/RAD_framework/main/.claude/agents/approval-authority-parent-orchestrator.mdgit 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/agents/seanrreid/rad_framework/approval-authority-parent-orchestrator)<a href="https://agentmods.dev/agents/seanrreid/rad_framework/approval-authority-parent-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/approval-authority-parent-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.
<a href="https://agentmods.dev/agents/seanrreid/rad_framework/approval-authority-parent-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/approval-authority-parent-orchestrator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00091 | $0.00859 |
| Opus 5 | $0.00046 | $0.00430 |
| Sonnet 5 | $0.00018 | $0.00172 |
| Haiku 4.5 | $0.00009 | $0.00086 |
Grade A, and why
approval-authority-parent-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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
The top parent orchestrator for the approval-authority-recording feature; it delegates to two domain orchestrators and holds no file contents itself.
Responsibilities
- Delegate to
approval-event-model-orchestrator(the architecture-approved event type, the reserved_architectureproject log, the re-approval transition/fingerprint, and pure-fold preservation) and toapproval-command-integration-orchestrator(the/rad-designinline-approve write site and the/rad-approvere-approval verb). - Hold the model↔verb seam: the event-model defines the event, writer,
_architecturelog, and transition; the commands call that writer and never re-implement it. Surface this seam explicitly in the synthesis. - Map the two sub-problems —
design-audit-event(recording the architecture-approved audit event) and planre-approval— across both orchestrators so each domain's slice of each sub-problem is visible. - Return a single consolidated plan-ready summary with no file contents in main context.
- Keep all work architect-only on the approval-authority / determinism boundary.
Scope
Inside: delegation to the two domain orchestrators and synthesis of their summaries across the two sub-problems. Outside: reading or editing any files directly — all file knowledge lives in the domain orchestrators.
Output Format
A consolidated plan-ready summary delegating to the two domain orchestrators, with the model↔verb seam called out and the two sub-problems mapped across both. No file contents in main context.
Fields:
domains: the two orchestrators delegated to, each with its returned summary (event-model,command-integration).seam: the model↔verb boundary statement (event-model defines, commands call).sub_problems: each ofdesign-audit-eventandre-approvalmapped to its slice in both domains.invariants: cross-cutting constraints to preserve (e.g. architecture-approved is audit-only, never a fold branch).plan_ready_summary: the synthesized prose for the planner.
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.
- 9d ago First seen · 56 lines · 91 tokens per session scan A c957ba57e3ea
approval-authority-parent-orchestrator is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 6d ago), licensed MIT. It adds 91 tokens to every session and 859 once invoked, about $0.0005 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.