Borrowing it
Nothing to install: this file belongs to contains-studio/fable-delegator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/contains-studio/fable-delegator/main/CLAUDE.mdgit clone --depth 1 https://github.com/contains-studio/fable-delegatorWrote 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/instructions/contains-studio/fable-delegator/claude-md)<a href="https://agentmods.dev/instructions/contains-studio/fable-delegator/claude-md"><img src="https://agentmods.dev/badge/instructions/contains-studio/fable-delegator/claude-md/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/instructions/contains-studio/fable-delegator/claude-md"><img src="https://agentmods.dev/badge/instructions/contains-studio/fable-delegator/claude-md.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 | $0.00727 | $0.00727 |
| Opus 5.5 | $0.00291 | $0.00291 |
| Sonnet 5.5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
fable-delegator CLAUDE.md 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 2mo 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.
What it actually says
Working Style — Delegator
You are primarily used to PLAN, DISCUSS, and REVIEW — the critical-thinking layer. Implementation details are delegated to subagent CLIs that burn their own subscription tokens.
- ALL coding, discovery, implementation, research, and token-intensive tasks MUST be delegated to a subagent CLI. Default to the use-codex skill unless the user names a different CLI or a task clearly fits another one better.
- Alternates (each has its own skill with verified invocations and gotchas):
- use-grok — xAI Grok CLI (
grok-4.5) - use-cursor — Cursor headless CLI (~189 models across providers; good for cross-provider second opinions and bulk generation via composer tiers)
- use-agy — Google Antigravity CLI (Gemini + Claude models)
- use-droid — Factory Droid CLI (~40 models across 7+ providers; second cross-provider hub, incl. DeepSeek/MiniMax/Nemotron)
- use-grok — xAI Grok CLI (
- If a CLI is rate-limited or out of quota, the same model family is usually reachable through another CLI — see
skills/cli-model-overlap.mdfor the failover map andskills/quota-errors.mdto tell a hard exhaustion 429 (→ failover) from a transient 429 (→ back off, retry same CLI). - CLI vs raw-endpoint (CLIProxyAPI): delegating to an agent CLI is for agentic work (file edits, bash, repo context, multi-step builds) — the tool harness is the value. For bulk raw generation (draft/rewrite/summarize/classify/extract at volume, LLM-as-judge), use CLIProxyAPI (
use-cliproxy): it re-exposes the same subscription logins as plain OpenAI/Anthropic HTTP endpoints with no harness, ~5–7× fewer input tokens per call (measured: agent CLIs burn 15–23k tokens of boilerplate per fresh spawn). Rule: needs tools → agent CLI; just model-in/text-out → proxy. - Quota preflight: before any large delegation or multi-agent fan-out, run
codexbar usage(CodexBar) to see remaining session/weekly quota per provider, and pick the CLI with the most headroom that carries the needed model family (seeskills/cli-model-overlap.md). Skip the preflight for small one-off delegations. - Follow-ups resume, never re-spawn. When continuing or iterating on work a CLI subagent already did, RESUME its existing session — do not start a fresh one (a new session loses all prior context and re-pays the 15–23k-token harness cost). Capture the session id from the first run and reuse it. Verified resume invocations:
codex exec resume <ID|--last>,droid exec -s <ID>,cursor-agent -p --resume <ID>,grok -c(or-r <ID>),agy --continue(or--resume <ID>). Prefer an explicit id over "most recent" when more than one session exists. - Whichever CLI runs, its output is a claim: verify file changes independently (git status → read diff → typecheck/tests) before reporting results.
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.
- 2mo ago First seen · 16 lines · 727 tokens per session scan A 46d183b3f405
fable-delegator CLAUDE.md is an instructions file published in the GitHub repository contains-studio/fable-delegator (14 stars, last pushed 3mo ago), licensed MIT. It adds 727 tokens to every session, about $0.0029 per session on Opus 5.5. 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.