Make your smartest AI the boss, not the typist
Fable Foreman turns your session into a job site.
A free, open-source skill for Claude Code: your strongest model becomes the foreman — it plans, routes, and reviews — while cheaper workers swing the hammers. And nothing gets called done until an independent verifier, who never saw how the work was built, reproduces the evidence.
Version 0.1.0 · Released July 10, 2026 · MIT licensed
You bought access to the smartest AI model on the planet — and then you asked it to rename variables for two hours.
That's like hiring a world-class architect and handing them a hammer. The expensive part of a frontier model is its judgment: what to build, what to check, what's actually wrong. The typing? A model a tenth the price does that just fine.
Fable Foreman flips that around. It's the management playbook nobody handed the boss — so your best model spends its time on the decisions only it can make, and the grunt work goes to workers who cost a fraction as much.
Get Fable Foreman
Free and MIT licensed. The repo is the home of the skill — grab it on GitHub, read the twelve small files in about ten minutes, and install it.
Install in Claude Code
Copy this and paste it into Claude Code. That's the whole install — Claude fetches the skill from GitHub and puts it where it belongs, along with its three agents. Works the same on Mac and Windows.
Install this skill globally on my machine: https://github.com/olsenbrands/fable-foremanClaude will show you exactly what it installed and where, so you can see it landed.
On Claude Desktop / claude.ai
Download the ZIP from the release page and upload it under Settings → Customize → Skills. Desktop runs a lighter “discipline mode” — the skill tells you plainly what it can and can't do there.
You've felt both of these
If you've run Claude Code hard, you know the two failure modes by heart:
“You hit your usage limit at 2pm because your frontier model spent the morning doing find-and-replace.”
“You told a swarm of agents to “just go” and watched an unsupervised budget evaporate on work nobody checked.”
The problem was never agents. It was that nobody gave the boss a management playbook.
What it actually does
Fable Foreman is instructions, not software — a skill your Claude reads and follows. No daemons, no config files, no hooks. Twelve plain-text files. Here's the system it installs in your AI's head:
- 1.
It probes the job site first.
What model is running? Can it spawn agents? Is OpenAI's Codex CLI installed and logged in? Foreman detects what your machine actually offers and adapts across five modes — from full orchestration down to an honest discipline mode on Claude Desktop that tells you exactly what it can't do there.
- 2.
It routes by judgment, not price list.
Tasks are classed FRONTIER, WORKHORSE, or FAST by their judgment content — a 500-line mechanical rename is FAST work; a 10-line concurrency fix is FRONTIER work. Each class then resolves to the cheapest model that clears the quality bar.
“Economics chooses among the models that clear the quality bar. It never lowers the bar.”— the First Law, verbatim from the skill
- 3.
It speaks both providers.
If you have Codex, Foreman can route work across OpenAI's tiers too — discovered from your account at runtime, chosen per task, and only with your explicit OK, because it's your money. No Codex? Everything falls back to Claude workers. Nothing breaks.
- 4.
Zero hardcoded models.
New Claude next month? New Codex tier? The rules never name dated models — they resolve live. It was built the week GPT-5.6 launched and survived that churn during its own review.
- 5.
It trusts no one — including itself.
Every meaningful change gets a blind verifier: fresh context, read-only tools, handed your original request (never the worker's retelling of it), and assuming the work is broken until it reproduces the evidence. When both providers are present, Claude verifies Codex's work and vice versa.
- 6.
It respects your budget in both directions.
Bounded retries (never a third identical attempt), announced fan-outs, one fix-worker per findings list instead of a swarm — and a degradation rule with a spine: if budget pressure would drop quality, it stops and tells you instead of quietly shipping worse work.
About the cost — the honest version
Anthropic has published that multi-agent systems can use roughly 15x the tokens of a single chat, and its own cost guidance recommends putting cheaper-tier workers under a stronger lead. Fable Foreman is built around exactly that.
So this is about smarter spend, not a discount. It won't promise to cut your bill by some percentage — subscription users all share one quota — but it does stop your most expensive model from doing your cheapest work, and it refuses to quietly burn budget on a runaway loop.
Built in public — and stress-tested by a rival AI
This skill wasn't vibe-coded in an afternoon. The research phase alone ran about 66 AI agents across three passes — reading every serious orchestration project on GitHub, the official Anthropic and OpenAI docs, and the failure post-mortems — before a line was written. Around 5.4M tokens, with every repo claim verified against the GitHub API.
Then the first draft went in front of the harshest reviewer available: GPT-5.6 “Sol,” OpenAI's flagship model, released that same week, running in a read-only sandbox with instructions to tear the draft apart. Across five adversarial review rounds the findings fell 21 → 12 → 10 → 7 → 2 → fixed. Sol caught things like a one-word bug where “commit or stash” would have made the verifier validate the wrong version of the code.
So the skill that teaches Claude to distrust AI self-reports was itself stress-tested by a rival AI until it stopped breaking. That's a stress test, not an endorsement — and the commit history on GitHub shows every round.
Who it's for
- →Claude Code users on Pro or Max who watch their usage bar like a gas gauge.
- →Anyone running big multi-file tasks who's been burned by unverified agent output.
- →People with both a Claude and a ChatGPT/Codex subscription who want them working as one team.
- →Claude Desktop users — you get a lighter but honest version that's upfront about its limits.
It's twelve files. Read them yourself.
No daemons, no telemetry, no magic. Fable Foreman is SKILL.md, four reference docs, three role agents — worker, scout, and verifier — and the manifests that register it. All plain text, MIT licensed, and it passes Anthropic's claude plugin validate. Read the whole system in about ten minutes, then decide — which is rather the point of a skill built on verifying instead of trusting.
Frequently asked questions
What is Fable Foreman?
A free, open-source skill for Claude Code. It makes your strongest model act as a foreman — it plans, routes, and reviews the work while cheaper models handle the mechanical parts — and every meaningful change is checked by an independent verifier before anything is called done.
Is it really free?
Yes. It's MIT licensed, version 0.1.0, released July 10, 2026. It's twelve plain-text files you can read in about ten minutes — no daemons, no config files, no telemetry.
Do I need an OpenAI Codex subscription?
No. Codex support is optional, auto-detected, and consent-gated. If you have Codex, Foreman can route work across OpenAI's tiers too — discovered from your account at runtime and only with your explicit OK, because it's your money. No Codex? Everything falls back to Claude workers and nothing breaks.
Will this lower my AI bill?
It's about smarter spend, not a discount. Anthropic has published that multi-agent systems can use roughly 15x the tokens of a single chat, and its own cost guidance recommends putting cheaper-tier workers under a stronger lead. Foreman keeps your most expensive model off your cheapest work — but subscription users share one quota, so it won't promise a percentage off your bill.
Does it work on Claude Desktop?
Yes, in a lighter 'discipline mode.' Desktop can't spawn parallel agents, so instead of pretending, the skill is honest about what it can't do there — you still get the routing and verification discipline in the work you do run.
Was it reviewed by OpenAI?
Its first draft went through five adversarial review rounds against GPT-5.6 'Sol' running in a read-only sandbox with instructions to tear it apart, and the findings dropped from 21 to zero blockers. That's a stress test, not an endorsement — the commit history on GitHub shows every round.
Make your best model the boss
Grab Fable Foreman on GitHub — free, MIT licensed, and small enough to read in about ten minutes.
Get it on GitHubDon't sleep on what's next
Get the next tool before everyone else
Free tools, prompts, and skills for Claude Code and OpenClaw — sent when they drop. No spam, unsubscribe anytime.
Also from Don't Sleep On AI
Build A Second Brain for Claude Code
Wire Obsidian into a persistent second brain for Claude Code with an automated installer. Auto-archive sessions, link topics, search past work — set up in about 2 minutes.
Keep exploring
More free AI tools and guides from Don't Sleep On AI
NEWThe Fable 5 Holy Grail of Skills
Three installs that turn Fable 5 into an orchestrator: Fable Foreman to plan and verify, the Codex CLI to do the typing, and the Fable Safe Prompt to keep you on Fable.
Prompt Fable 5 Without Security Triggers
A free prompt that turns Opus 4.8 into a Fable-safe prompt writer, so security and biology classifiers stop misreading legitimate work.
UPDATED — v1.1Give Codex Full Local Access
A free Codex prompt that configures the Codex app and CLI for approval-free, full local access — then runs a proof so you know it took effect.
Your frontier model is worth more than grunt work. Put it in charge.
Don't sleep on AI.
