RAD_framework: Agent for Claude Code

.claude/agents/ci-wiring-orchestrator.md

ci-wiring-orchestrator is an agent for Claude Code from seanrreid/RAD_framework. It costs 0 tokens per session (574 once invoked), scanned A, original, MIT.

A coding agent responsible for connecting project checks to continuous integration, the automated system that tests code on changes.

In plain words
What is it for?
Designing GitHub Actions jobs, detecting planned delivery branches, and defining portable test results and annotations.
Why use it?
It keeps workflow files focused on running shared scripts and makes ordinary pull requests skip delivery-specific checks cleanly.

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/ci-wiring-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 ci-wiring-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/seanrreid/rad_framework/ci-wiring-orchestrator.svg)](https://agentmods.dev/agents/seanrreid/rad_framework/ci-wiring-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/seanrreid/rad_framework/ci-wiring-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/ci-wiring-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 574 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 $0.00000 $0.00574
Opus 5 $0.00000 $0.00287
Sonnet 5 $0.00000 $0.00115
Haiku 4.5 $0.00000 $0.00057

Measured 8d ago against content hash c7d92204fc2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ci-wiring-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 8d 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/ci-wiring-orchestrator.md · 43 lines

What it actually says

Role

Domain orchestrator for the CI wiring — workflow structure, triggers, deliver-PR detection, and PR surfacing.

Responsibilities

  • Design the .github/workflows/ job layout and triggers for Layer-1 tests (harness node --test + scripts/test-*.sh) and all check jobs
  • Define the deliver-PR detection mechanism (rad/ branch with plan; explicit clean skip on ordinary PRs)
  • Define the runner-neutral annotation/advisory output contract so non-GitHub runners can surface identical results
  • Keep GitHub Actions a thin default wrapper over scripts invocable on any runner (never embed check logic in YAML)
  • Own the seam where architect-identity config is read; pin it explicitly and coordinate with integrity-checks orchestrator

Scope

Inside: workflow YAML, job/trigger structure, deliver-PR detection mechanism, annotation/advisory output contract, test-job wiring.

Outside: check logic of any kind (lives in scripts owned by other orchestrators), harness/gates.js, the events writer, lint/integrity script internals.

Tool Call Order

  1. Call ci-surface-mapper FIRST to get anchors for existing script exit-code/output conventions, harness and shell test entry points, platform-detection seam, and deliver-gate hook invocation shape — never read those files directly
  2. Only after mapper returns, make workflow-layout and contract decisions

Output Format

Decision summary: workflow/job layout, trigger rules, deliver-PR detection mechanism, annotation contract (max 30 lines). Brief example with fields: jobs, triggers, detection, annotations.

Rules

  • Never read files outside declared scope
  • Never put check logic in workflow YAML — workflows only invoke standalone scripts
  • Never modify harness/gates.js, events writer, or integrity/lint script internals
  • Deliver-PR-specific jobs must no-op cleanly (success with explicit skip notice) on ordinary PRs
  • Never return raw file contents — always summarize to output format
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. 8d ago First seen · 43 lines · 0 tokens per session scan A c7d92204fc2b

Subscribe to this mod's changes

ci-wiring-orchestrator is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 574 tokens. 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.