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.
npx skills add oscarsterling/clelp-skills --skill orchestrator-hooksgit clone --depth 1 https://github.com/oscarsterling/clelp-skillsWrote 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/skills/oscarsterling/clelp-skills/orchestrator-hooks)<a href="https://agentmods.dev/skills/oscarsterling/clelp-skills/orchestrator-hooks"><img src="https://agentmods.dev/badge/skills/oscarsterling/clelp-skills/orchestrator-hooks/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/skills/oscarsterling/clelp-skills/orchestrator-hooks"><img src="https://agentmods.dev/badge/skills/oscarsterling/clelp-skills/orchestrator-hooks.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 | $0.00055 | $0.01801 |
| Opus 5 | $0.00028 | $0.00901 |
| Sonnet 5 | $0.00011 | $0.00360 |
| Haiku 4.5 | $0.00006 | $0.00180 |
Grade B, and why
orchestrator-hooks scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.claude/settings.json` (user scope), `.claude/settings.json` (project How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator Hooks
You are setting up the "expensive brain orchestrates, cheap models build" pattern on the user's Claude Code install. The goal is a PreToolUse hook that mechanically enforces two rules whenever the main session is running on the user's most expensive "orchestrator" model:
- The orchestrator main session must NOT author code (Write/Edit/NotebookEdit on code files). Docs and config writes stay allowed.
- Every sub-agent spawn (Agent tool) must pin an explicit builder model, so orchestrator capacity is never silently spent on delegated work.
Together these create a delegation loop: the orchestrator cannot write code, so it spawns a builder sub-agent, and the sub-agent does the writing.
You will INSPECT the user's setup, GENERATE a hook fitted to it, WIRE it into their settings with a backup, and VERIFY it blocks a code write. Do not just copy the reference file blindly. Read the setup first, then generate.
reference/orchestrator-guard.example.py in this skill is the known-good
reference implementation. Treat it as the source of truth for the algorithm.
Your generated hook should match its logic and only differ where the user's
setup differs.
Step 1: Inspect the setup
Gather these facts before writing anything. Ask the user only for what you cannot determine yourself.
- Settings location. Check, in order, for a hooks-capable settings file:
~/.claude/settings.json(user scope),.claude/settings.json(project scope),.claude/settings.local.json(local scope). Confirm with the user which scope they want the guard to apply to. Read the chosen file. - Orchestrator model marker. Ask which model is the expensive orchestrator
(for example an Opus-class or otherwise premium model). You need a substring
that appears in that model's harness id (case-insensitive), for example
opus. This is the marker the hook keys off. - Builder model. Ask which model sub-agents should be pinned to (a cheaper or faster model). The hook does not hard-code this; it only requires that spawns pin SOME explicit model that is not the orchestrator. Record it so you can tell the user what to pass.
- Existing hooks. Read the settings
hooks.PreToolUsearray. Note any existing matcher coveringEdit|Write|NotebookEdit|Agentso you do not create a conflicting or duplicate entry. If an orchestrator guard is already wired, switch to audit/repair mode instead of adding a second one. - Companion security hook (carve-out). Ask whether the user has any other hook that forbids sub-agents from editing certain sensitive files (hook scripts, settings, agent definitions). If yes, those files are main-session-only and must be carved out of Rule 1, or the change deadlocks (no author allowed). Collect those paths. If no such hook exists, the carve-out lists stay empty.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 146 lines · 55 tokens per session scan B 23694e18b585
orchestrator-hooks is a skill published in the GitHub repository oscarsterling/clelp-skills (0 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 1,801 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…