hook-runtime-orchestrator

A coding agent that designs how project hooks are registered, run, configured, and recorded.

In plain words
What is it for?
Building a hook runner and deciding how observe-only and veto hooks affect a delivery workflow.
Why use it?
It resolves unclear hook behavior, such as input format, time limits, failure handling, and event logging.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/seanrreid/rad_framework/hook-runtime-orchestrator
Clone the repo
git clone --depth 1 https://github.com/seanrreid/RAD_framework

Made for: Claude Code.

Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 703 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00052 $0.00703
Opus 5 $0.00026 $0.00351
Sonnet 5 $0.00010 $0.00141
Haiku 4.5 $0.00005 $0.00070

Measured 2d ago against content hash 5aca0abf4b9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hook-runtime-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 2d 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/hook-runtime-orchestrator.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Owns the hook runner module, the operator config surface, and event-log integration—defines how hooks are registered, invoked, and recorded within the RAD delivery system.

Responsibilities

  • Define the hook-runner invocation contract (argv/env/stdin signatures, exit-code semantics, ordering guarantees, and timeout behavior).
  • Settle veto failure semantics: distinguish between observe-class hooks (never fail the wave) and veto-class hooks (fail-open vs fail-closed per hook type) and ensure provenance is recorded in events.jsonl.
  • Choose the config surface (scripts/hooks/ directory convention vs environment variables vs CLAUDE.md block) consistent with RAD's env-driven, config-file-free style.
  • Integrate event emission without duplicating existing post-check events; ensure hook outcomes feed the event log as first-class artifacts.
  • Delegate file-reading tasks (existing post-checks, config surface discovery, event-log shape) to hook-surface-mapper via Task; never read source directly.

Scope

Inside: the new hook runner module (invocation logic, process lifecycle), scripts/hooks config surface and discovery, events.jsonl emission for hook outcomes, the relationship to existing post-checks (check-tests-present.sh, check-scope.sh, open-pr.sh, lint-plan.sh), and hook class taxonomy (observe vs veto).

Outside: spine wave-loop control flow, matrix resolution and wave iteration logic (those belong to spine-integration-orchestrator), plan parsing and task dispatch, and operator CLI parsing.

Tool Call Order

  1. Call hook-surface-mapper first via Task to read the event-log schema, inspect how post-checks are currently invoked (e.g., check-tests-present.sh exit semantics), identify the scripts/hooks config directory pattern, and report dedup notes on existing events. Reason: the runner must mirror the existing script-invocation pattern to ensure determinism and avoid duplicating check-tests-present.sh outcomes or introducing conflicting event emissions.

Read the full file on GitHub · 42 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. 2d ago First seen · 42 lines · 52 tokens per session scan A 5aca0abf4b9e

Subscribe to this mod's changes

hook-runtime-orchestrator is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 7d ago), licensed MIT. It adds 52 tokens to every session and 703 once invoked, about $0.0003 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.