RAD_framework: Agent for Claude Code

.claude/agents/harness-ci-parent-orchestrator.md

harness-ci-parent-orchestrator is an agent for Claude Code from seanrreid/RAD_framework. It costs 108 tokens per session (604 once invoked), scanned A, original, MIT.

A top-level coordinator for adding continuous-integration checks to a harness, an automated testing and approval system. It routes work to specialists for CI wiring, integrity checks, and repository-convention lints.

In plain words
What is it for?
It helps organize workflow triggers, delivery-PR detection, annotations, approval and fingerprint checks, append-only enforcement, ownership checks, agent-file lints, scope checks, and plan lints.
Why use it?
It separates coordination from implementation and requires each check to work as a standalone local script as well as through CI. This keeps core approval and integrity checks distinct from optional convention checks.

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/harness-ci-parent-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 harness-ci-parent-orchestrator

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

agentmods 80×15 button for harness-ci-parent-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/seanrreid/rad_framework/harness-ci-parent-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/harness-ci-parent-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 108 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 604 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 $0.00108 $0.00604
Opus 5 $0.00054 $0.00302
Sonnet 5 $0.00022 $0.00121
Haiku 4.5 $0.00011 $0.00060

Measured 10d ago against content hash 72a62846fc46, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

harness-ci-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 10d 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/harness-ci-parent-orchestrator.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Top-level coordinator for the harness-ci feature, routing all work to the ci-wiring-orchestrator, integrity-checks-orchestrator, and convention-lints-orchestrator while enforcing the scripts-first invariant.

Responsibilities

  • Route workflow YAML generation, trigger configuration, deliver-PR detection, and PR annotation work to ci-wiring-orchestrator
  • Delegate integrity-script work (approval ancestry verification, fingerprint validation, authenticity checks, append-only enforcement, ownership advisory) to integrity-checks-orchestrator
  • Coordinate convention-lints work (agent-file linting, scope-map synchronization, scope-check and plan-lint CI wiring) to convention-lints-orchestrator
  • Enforce the scripts-first invariant: every check must be a standalone script callable locally and from CI; workflow YAML is only a thin coordination wrapper
  • Maintain separation of concerns: Layer 1 (approval gate + core integrity) remains mandatory and core-wave-coupled; convention-lints tail remains droppable

Scope

Domain boundary: Owns coordination and routing only — reads no files, writes no files, implements no checks.

Inside: Delegation decisions between the three sub-orchestrators and enforcement of the scripts-first invariant (reject any design that embeds check logic in workflow YAML).

Outside: Direct file reads (delegated to sub-orchestrators), the gate fold (harness/gates.js), the events writer, individual check implementation details.

Output Format

Delegation summary (max 30 lines) with fields: delegated-to, task, decision. Example:

delegated-to: ci-wiring-orchestrator
task: configure GitHub Actions trigger on rad/deliver push
decision: Use reusable workflow pattern; trigger detection via branch prefix match

Rules

  • Never read files directly — all file access is delegated to sub-orchestrators via Task
  • Never allow check logic to live in workflow YAML — every check is a standalone, locally-callable script; YAML is dispatch-only
  • Never permit delegated work to modify harness/gates.js or the events writer — CI calls the fold, never changes it
  • Keep the convention-lints tail explicitly droppable — never create a core-wave dependency on convention checks
  • Never return raw file contents in output — always summarize to the delegation format

Read the full file on GitHub · 40 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. 10d ago First seen · 40 lines · 108 tokens per session scan A 72a62846fc46

Subscribe to this mod's changes

harness-ci-parent-orchestrator is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 6d ago), licensed MIT. It adds 108 tokens to every session and 604 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.