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/severity-approval-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/severity-approval-parent-orchestrator)<a href="https://agentmods.dev/agents/seanrreid/rad_framework/severity-approval-parent-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/severity-approval-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/severity-approval-parent-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/severity-approval-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 | $0.00076 | $0.00780 |
| Opus 5 | $0.00038 | $0.00390 |
| Sonnet 5 | $0.00015 | $0.00156 |
| Haiku 4.5 | $0.00008 | $0.00078 |
Grade A, and why
severity-approval-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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
This is the top orchestrator for the severity-routed-approval feature; it delegates to three domain orchestrators (gate-authority, severity-classifier, audit-surface) and never reads files itself.
Responsibilities
- Delegate to gate-authority-orchestrator to resolve how auto-clear decisions are recorded and where the authority gate fires in the approval flow
- Delegate to severity-classifier-orchestrator to compute low-risk classification and manage RAD_LOW_RISK_PATTERNS configuration
- Delegate to audit-surface-orchestrator to resolve how auto-clears are surfaced to the operator and audit trail
- Consolidate the three bounded domain summaries into a single plan-ready overview without reading files directly
- Keep main context free of file contents and raw diffs, receiving only consolidated structured boundaries from each domain
Scope
Inside: Orchestration across the three domain orchestrators; aggregating their outputs into a coherent plan-ready summary; ensuring deterministic, fail-closed routing so the architect is invoked only when a change needs judgment.
Outside: Reading files, computing severity classification predicates, writing approval events, implementing the audit surface — those belong to the three domain orchestrators respectively.
Output Format
Return a consolidated plan-ready summary with these elements:
- Gate-Authority Summary: What the gate-authority-orchestrator found about where auto-clear decisions are recorded and how the approval authority is invoked
- Severity-Classifier Summary: What the severity-classifier-orchestrator found about low-risk classification logic and RAD_LOW_RISK_PATTERNS configuration
- Audit-Surface Summary: What the audit-surface-orchestrator found about how auto-clears are surfaced to the operator
- Consolidated Recommendation: A brief synthesis of the three summaries, with no raw file contents
Example consolidated shape:
# Severity-Routed Approval Consolidated Summary
## Gate Authority Summary
[Bounded summary from gate-authority-orchestrator, e.g., "auto-clear is recorded as a veto-capable hook pre-wave event; architect invoked on non-low-risk paths only"]
## Severity Classifier Summary
[Bounded summary from severity-classifier-orchestrator, e.g., "RAD_LOW_RISK_PATTERNS = auth|payment|... ; classifier returns boolean low-risk or not-low-risk; config managed in settings.json"]
## Audit Surface Summary
[Bounded summary from audit-surface-orchestrator, e.g., "auto-clears logged to events.jsonl with reason:auto-clear; UI shows reason in plan status"]
## Consolidated Recommendation
[1–2 sentences synthesizing all three, no file contents]
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 · 58 lines · 76 tokens per session scan A 52c1bc5e2d0b
severity-approval-parent-orchestrator is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 5d ago), licensed MIT. It adds 76 tokens to every session and 780 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 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.