Fable-ish Verification Discipline
Risk-proportional verify-before-you-claim-done workflow for coding tasks, ported from a Codex plugin.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 14, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · c396091
Ran it against a fake 'login returns 500 on empty password' bug: it forced a reproduce-the-500-first step and named the exit proof (400 returned, re-run of the same repro) before allowing the fix, then closed with a standard 'what changed / commands run / results / known gaps' report -- baseline jumped straight to 'add a check' with no repro or re-verification step.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 5/5
What Fable-ish Verification Discipline does
Classifies each coding task as quick/normal/deep/blocked, then enforces a reproduce-first work loop that names an observable exit proof before implementing, runs the narrowest relevant verification, and reports only evidence-backed claims in a standard final-report shape. Triggers on 'fable-ish'/'fablish' requests, complex implementation, debugging, refactoring, or deployment prep; explicitly opts out for simple explanations or quick low-risk answers.
How to install Fable-ish Verification Discipline
git clone https://github.com/chrisryugj/fable-ish
cd fable-ish
mkdir -p ~/.claude/skills
cp -r skills/fable-ish ~/.claude/skills/fable-ish
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Fable-ish Verification Discipline
-
/fable-ishRisk-proportional verify-before-you-claim-done workflow for coding tasks, ported from a Codex plugin.
It also activates on plain-language prompts like these:
-
Implement this and prove it works before you call it done -
Refactor the auth flow with evidence at each step -
Debug this failure and show me the verification you ran
Frequently asked questions
- Is the Fable-ish Verification Discipline skill free?
- Yes. The skill itself is free from chrisryugj/fable-ish. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Fable-ish Verification Discipline work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Ran it against a fake 'login returns 500 on empty password' bug: it forced a reproduce-the-500-first step and named the exit proof (400 returned, re-run of the same repro) before allowing the fix, then closed with a standard 'what changed / commands run / results / known gaps' report -- baseline jumped straight to 'add a check' with no repro or re-verification step.
- What is the Fable-ish Verification Discipline SkillProof Score?
- 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
- How do I install Fable-ish Verification Discipline?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Fable-ish Verification Discipline with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.