agentleFS
Sign inStart free
imMamdouhaboammarimMamdouhaboammar/get-fable/SKILL.md

get-fable

Skill6 starsChanged 3 months agoMITView on GitHub

Portable coding lifecycle and continuous situational awareness for AI agents across 25 specialist skills and canonical packs.

The file

Create a free account to mount
Files
SKILL.md

get-fable

A complete coding lifecycle governance kernel for AI agents.

Core Routing & Specialists

Core Pack (core)

  • get-fable: Universal front-door router and orchestrator
  • fable-discover: Grounding and execution path exploration
  • fable-plan: Architecture, migration plans, and task decomposition
  • fable-execute: Focused implementation within bounded cards
  • fable-verify: Machine-checked test, build, and runtime evidence
  • fable-recover: Deterministic failure diagnosis and loop recovery

Intelligence & Build Packs (intelligence, build)

  • fable-research: Primary source and official documentation research
  • fable-tdd: Test-driven development with red-green verification
  • fable-delegate: Bounded parallel work delegation across subagents

Proof & Delivery Packs (proof, delivery, evolution)

  • fable-review: Independent diff and correctness review
  • fable-security: Security boundary review and threat mitigation
  • fable-release: Release readiness, packaging, and version consistency
  • fable-handoff: Context preservation and next-session handoffs
  • fable-eval: Holdout evaluation and benchmark scoring

System & Harness Pack (system)

  • fable-dataviz: Accessible data visualizations, charts, plots, and dashboards
  • fable-artifact: Structured technical proposals, responsive artifacts, and diagrams
  • fable-simplify: Zero-regression code simplification and altitude cleanup
  • fable-loop: Bounded recurring task loops and interval polling
  • fable-run: Live app runtime execution and smoke testing
  • fable-memory: Persistent file-based memory system and knowledge indexing
  • fable-config: Agent harness parameters, allowlist permissions, and hook configuration
  • fable-simulator: Rigorous truthfulness, independent verification oracles, and contract derivation
  • fable-cowork: Autonomous cowork execution, silent tool chaining, and safety boundaries
  • fable-spark: Situational awareness micro-policy predicting atomic next moves

Creator Pack (creator)

  • skill-creator: Author, refine, benchmark, and package autonomous skills with evaluation suites

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free