fable
Skill0 starsChanged 4 months agoMITView on GitHub
Run ONE hard reasoning/planning task on Fable 5 as a subagent, without leaving your current (Opus/Sonnet) seat. Use when you're on a cheaper model mid-session and hit a problem that genuinely needs frontier judgment — a subtle design call, a deep analysis, a strategic tradeoff — and want Fable's depth on just that piece. The main loop stays on the cheap model; only this one sub-task runs at Fable rates; only its distilled answer returns to context. Triggers - "fable this", "reason this on fable", "run this on fable", "/fable", "fable-reason".
13 other projects use a version of this.
Adopted by
Most recently taken up by
- michaelczesun/poor-mans-fabletheir own version, first seen Oct 20, 2026
- thedigitalorganizer/soloshiptheir own version, first seen Oct 15, 2026
- Lesani/skillstheir own version, first seen Oct 11, 2026
- Junhan2/oh-my-fabletheir own version, first seen Oct 10, 2026
- romangalaxys10-spec/fabletheir own version, first seen Oct 8, 2026
- blueskynnn-cloud/claude-skillstheir own version, first seen Aug 28, 2026
Used with
Projects with it also use implement, review and 1 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- Junhan2/oh-my-fable★ 57same name
- tdimino/claude-code-minoan★ 41same name
- romangalaxys10-spec/fable★ 4same name
- akhilguptahub/fable-skill★ 3same name
- cookiesheep/fable-skill★ 1same name
- gfsaaser24/fable-power-up★ 1same name
- Lesani/skills★ 1same name
- blueskynnn-cloud/claude-skills★ 0same name
- Hesstastic/fable-agent-orchestration★ 0same name
- michaelczesun/poor-mans-fable★ 0same name
3 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- conversion-systemSkill
- goalSkill
- graph-loopSkill
- handoffSkill
- karpathy-guidelinesSkill
- managerSkill
- outer-loopSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Seat check: If the current main-loop model is *already Fable*, just answer in-chair — no subagent needed.
- Very specific: line 35
If you need several rounds of pushing on it, launch the fable seat instead (the fable shell alias) and work there.
“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/fable — one hard reasoning call on Fable, from any seat
You are (probably) on Opus/Sonnet. A skill does not switch your model. To get Fable's judgment on one piece without switching your whole session to Fable, delegate that piece to a Fable subagent and stay put.
How to run
- Seat check. If the current main-loop model is already Fable, just answer in-chair — no subagent needed. Otherwise continue.
- Spawn ONE
Agentwithmodel: fable. Give it the context floor — it starts blank, so pass everything it needs to reason well:- the exact problem/question,
- the relevant conversation context, constraints, and any decisions already made,
- what a good answer looks like (the decision to make, options on the table, the tradeoff axis),
- instruction to return a distilled answer — the conclusion + the key reasoning, not a raw think-aloud dump.
- Relay the subagent's answer to the user. Add your own one-line framing only if it helps; don't re-reason it on the cheap seat (that defeats the point).
When NOT to use
- Iterative, multi-round hard thinking — a single subagent call is one-shot.
If you need several rounds of pushing on it, launch the
fableseat instead (thefableshell alias) and work there. - Mechanical / light work — that's haiku/sonnet, not Fable. Don't burn Fable rates on extraction, sweeps, or drafting.
- A whole mixed task — use
manager(it routes each piece, escalating to a Fable subagent only for the frontier parts).
Cost note
Main seat pays only for: writing the brief + reading the distilled answer. Fable
pays only for the reasoning itself. Strictly cheaper than sitting on Fable for the
session, and you keep Fable-tier depth on the part that needs it. Pairs with
the manager skill and a review-loop's planning phase,
which use the same fable-subagent-from-any-seat mechanism.
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.