Plugin fable
The Fable Workflow: think (fable-method), act (fable-loop), prove (fable-judge), grow (fable-domain). A problem-solving loop, its orchestration, an adversarial work-verifier, and a domain-adapter generator, with the eval that keeps them honest.
Comment installer le plugin fable
Exécutez les deux commandes dans Claude Code. La première ajoute la marketplace une seule fois ; la seconde installe le plugin.
/plugin marketplace add Sahir619/fable-method
/plugin install fable@fable-methodContenu de fable
4 parties lues depuis les fichiers du plugin.
Skills 4
Claude le charge quand la tâche correspond- fable-domain
Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke eval. Use when the user says "/fable-domain SECTOR", "make a skill for DOMAIN", "add a domain to the fable method", or "give a lesser model Fable's workflow for DOMAIN". The bundle is the deliverable; a workflow without its flowchart, sources, and trap is not done.
- fable-judge
Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened tests and false completion claims, and delivers an evidence-based verdict (VERIFIED / VERIFIED WITH CAVEATS / REFUTED). Use after any agent or model claims work is complete - "/fable-judge", "judge this work", "verify what it did", "did that actually work?". Also runs the fable-method trap suite against a skill or model via "/fable-judge suite TARGET".
- fable-loop
End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification agents, honest outcome-first report. Use for non-trivial multi-step tasks when the user says "/fable-loop", "run the fable loop", or "do this the way Fable would". For the rules alone without orchestration, use fable-method; for large multi-phase projects, prefer the GSD workflow and use this inside phases.
- fable-method
A step-by-step problem-solving loop (classify the ask, define done, gather evidence, decide, act surgically, verify by observation, report outcome-first). Use when the user says "/fable-method", "use the fable method", or "approach this like Fable", or proactively when starting any multi-step task that no task-specific skill covers. Subcommands - plan (stop after the plan), audit (grade finished work against the loop), report (rewrite an answer outcome-first).
Utiliser fable dans Claude Code
Les Skills ne nécessitent pas de commande. Claude les lit quand votre requête correspond à leur description.
Mettre à jour, désactiver ou supprimer
- Mettre à jour le plugin (shell)
- claude plugin update fable@fable-method
- Actualiser le marketplace
- /plugin marketplace update fable-method
- Le désactiver pour le moment
- /plugin disable fable@fable-method
- Le supprimer
- /plugin uninstall fable@fable-method
Skills dans fable
- fable-domainSahir619/fable-method
Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke eval. Use when the user says "/fable-domain SECTOR", "make a skill for DOMAIN", "add a domain to the fable method", or "give a lesser model Fable's workflow for DOMAIN". The bundle is the deliverable; a workflow without its flowchart, sources, and trap is not done.
2 fichiers2,3 kétoiles - fable-judgeSahir619/fable-method
Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened tests and false completion claims, and delivers an evidence-based verdict (VERIFIED / VERIFIED WITH CAVEATS / REFUTED). Use after any agent or model claims work is complete - "/fable-judge", "judge this work", "verify what it did", "did that actually work?". Also runs the fable-method trap suite against a skill or model via "/fable-judge suite TARGET".
2 fichiers2,3 kétoiles - fable-loopSahir619/fable-method
End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification agents, honest outcome-first report. Use for non-trivial multi-step tasks when the user says "/fable-loop", "run the fable loop", or "do this the way Fable would". For the rules alone without orchestration, use fable-method; for large multi-phase projects, prefer the GSD workflow and use this inside phases.
2 fichiers2,3 kétoiles - fable-methodSahir619/fable-method
A step-by-step problem-solving loop (classify the ask, define done, gather evidence, decide, act surgically, verify by observation, report outcome-first). Use when the user says "/fable-method", "use the fable method", or "approach this like Fable", or proactively when starting any multi-step task that no task-specific skill covers. Subcommands - plan (stop after the plan), audit (grade finished work against the loop), report (rewrite an answer outcome-first).
14 fichiers2,3 kétoiles
Questions sur le plugin fable
Comment installer le plugin fable ?
Dans Claude Code, exécutez /plugin marketplace add Sahir619/fable-method, puis /plugin install fable@fable-method.
Que contient le plugin fable ?
fable regroupe 4 skills.
Comment mettre à jour ou supprimer le plugin fable ?
Mettez-le à jour avec claude plugin update fable@fable-method dans votre shell, ou depuis l'onglet Installed de /plugin. Supprimez-le avec /plugin uninstall fable@fable-method.
Sous quelle licence est le plugin fable ?
MIT, comme indiqué dans le manifeste du plugin.