#235235th of 259 in Skills, plugins and prompts
fable-method
Claude Code plugin with four skills for a classify, verify, report workflow
- Stars
- 2.3k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Jul 2026
- Language
- Python
0 on 7 Jul 20262,302 on 20 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Packages a stepwise agent workflow as four skills: fable-method (classify the ask, define done, gather evidence, decide, act, verify, report), fable-loop (orchestrated subagent run), fable-judge (adversarial check of finished work) and fable-domain (generates domain adapters). Installs as a Claude Code plugin or Codex skills, with AGENTS.md for other harnesses. The repo includes eval logs from fifteen rounds and 260+ runs, self-described as smoke-test grade.
Who it is for: Claude Code and Codex users who want agents to verify their own work
Strengths
- Every rule is tied to a committed eval transcript and per-scenario case study
- fable-judge re-runs claimed checks and diffs changes to catch false completion reports
- Installs as a Claude Code plugin, Codex skills, or AGENTS.md for other agents
- Eight domain adapters load lazily; eval nulls and failures are logged beside the wins
Weaknesses
- Evals are 1-4 runs per cell with LLM judges; the README calls them smoke-test grade
- No measured lift on ordinary small tasks with capable models
- Haiku surfaced the skipped-deploy decision in only 1 of 12 runs
- Seven of the eight domain adapters lack sourced references; medical has none
What it needs
- no GPU
- Needs Claude Code or Codex
- Models: Claude Haiku, Claude Sonnet, Claude Opus
Also in Skills, plugins and prompts
See all 259| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |
| 3 | skillsAgent skills for planning, TDD, debugging and code review | 94 out of 100 |
| #4 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 94 out of 100 |
| #5 | oh-my-claudecodeMulti-agent orchestration plugin and CLI for Claude Code | 94 out of 100 |