100yenadmin100yenadmin/fable-token-saving-skills-orchestrator/skills/fable-orchestrator-router/SKILL.mdfable-orchestrator-router
Skill100 starsChanged 4 months agoMITView on GitHub
Use before delegating work from a Fable or premium-model orchestration session.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- codex-dispatchSkill
- public-readme-polisherSkill
- public-repo-operationalizerSkill
- run-economicsSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Before dispatching, score the unit:
- Distinctive: line 34
Every dispatched lane gets:
- Distinctive: line 43
Every returned lane must be judged by output quality.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Fable Orchestrator Router
Fable owns judgment. Cheaper lanes do bounded work.
Routing Pass
Before dispatching, score the unit:
- complexity: trivial, standard, complex, frontier
- urgency: blocking now or parallel
- context locality: local tools needed or self-contained
- taste: user-facing judgment or mechanical
- volume: one task or many similar tasks
Lane Choices
- Fable: strategy, architecture, decomposition, dispatch packet, review, synthesis, taste, final judgment.
- Deep reasoner: hard bounded reasoning legwork.
- Coder: complex repo-native implementation.
- Fast worker: mechanical coding, tests, docs, digest duty.
- Codex or side worker: well-specified implementation, side PR, blind review, UI verification.
- Budget lane: non-urgent slow batch work.
- Tiny lane: high-volume machine-checkable fan-out.
Output Contract
Every dispatched lane gets:
- objective
- files or surfaces involved
- what not to touch
- acceptance criteria
- proof boundary
- expected artifact or report shape
Every returned lane must be judged by output quality. Escalate one tier up if the result misses the bar.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.