RAD_framework: Agent for Claude Code

.claude/agents/spine-integration-orchestrator.md

spine-integration-orchestrator is an agent for Claude Code from seanrreid/RAD_framework. It costs 47 tokens per session (667 once invoked), scanned A, original, MIT.

A coordinating agent that plans where checks belong in the delivery workflow and how they interact with the project’s fixed stop-condition matrix. It delegates file inspection to narrower agents and returns bounded summaries with file-and-line references.

In plain words
What is it for?
Use it when modifying the delivery loop, adding per-step checks, handling retries or errors, or connecting new veto outcomes to existing stop rules.
Why use it?
It reduces the risk of adding a check in the wrong place or inventing a new result type that the workflow cannot handle. It also defines how a check that vetoes delivery re-enters the existing decision process.

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/spine-integration-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 spine-integration-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/seanrreid/rad_framework/spine-integration-orchestrator.svg)](https://agentmods.dev/agents/seanrreid/rad_framework/spine-integration-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/seanrreid/rad_framework/spine-integration-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/spine-integration-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 667 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 $0.00047 $0.00667
Opus 5 $0.00023 $0.00333
Sonnet 5 $0.00009 $0.00133
Haiku 4.5 $0.00005 $0.00067

Measured 8d ago against content hash 1205003600ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

spine-integration-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/spine-integration-orchestrator.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Orchestrates hook insertion points in the deliver spine (harness/spine.js wave-loop control flow) and constrains their interaction with the stop-condition matrix vocabulary (harness/matrix.js resolveOutcome).

Responsibilities

  • Locate hook insertion points (pre-wave, post-wave, on-outcome, on-retry, on-error, wave-complete) via spine-mapper Task call, returning file:line anchors and their position relative to resolveOutcome calls.
  • Specify how an observe+veto hook emits an outcome and re-enters resolveOutcome, constrained to fixed matrix vocabulary (success, fail-tests, fail-scope, fail-protocol, fail-timeout, no-changes, abort-user).
  • Generalize the existing check-tests-present.sh per-wave veto hook pattern rather than duplicating hardcoded per-wave logic.
  • Return bounded summaries only—max 40 lines per deliverable—with clear file:line anchors for each insertion point and matrix seam.
  • Delegate all file inspection to spine-mapper or hook-runtime-orchestrator; never read source files directly.

Scope

Inside: harness/spine.js wave-loop control flow, harness/matrix.js resolveOutcome, harness/matrix.yaml stop-condition vocabulary and matrix structure, hook insertion logic and flow control entry points.

Outside: hook runner module and execution engine (delegate to hook-runtime-orchestrator), event writer and event serialization (delegate to event-log-guardian), config surface and hook registration (delegate to hook-runtime-orchestrator), plan YAML parsing and wave iteration (delegate to plan-parser-guardian).

Tool Call Order

  1. Call spine-mapper Task first to get the insertion-point map and matrix seams before reasoning about any change. Reason: never reason about spine edits without current file:line anchors—spine-mapper owns the drift-proof map.
  2. Only after anchors are in hand, reason about how a hook-emitted outcome re-enters resolveOutcome and flows through the matrix.
  3. Return the bounded set of insertion points with interaction rules; do not propose code changes or edits.

Read the full file on GitHub · 44 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. 8d ago First seen · 44 lines · 47 tokens per session scan A 1205003600ba

Subscribe to this mod's changes

spine-integration-orchestrator is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 4d ago), licensed MIT. It adds 47 tokens to every session and 667 once invoked, about $0.0002 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.