Skip to content
Back to skills

Prompts

ASecurity

Compatibility alias for the canonical get-fable coding lifecycle. Use when the user explicitly asks for Fable mode or when an existing installation invokes this legacy skill name.

  • 7 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 3, 2026
ai-agentsgosecurity

Security analysis

A100/100

Pro scans all 21 files and shows the line behind each finding

Scanned September 3, 2026

npx -y skills add imMamdouhaboammar/get-fable --skill prompts --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Prompts?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Prompts
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/immamdouhaboammar-prompts/badge)](https://www.skillsdirectory.com/skills/immamdouhaboammar-prompts)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: fable-mode
description: Compatibility alias for the canonical get-fable coding lifecycle. Use when the user explicitly asks for Fable mode or when an existing installation invokes this legacy skill name.
triggers:
  - "fable mode"
  - "fable-mode"
  - "use fable mode"
  - "work like Fable 5"
  - "rigorous mode"
  - "fable 模式"
  - "开 fable-mode"
  - "像 Fable 5 一样做"
  - "严谨模式"
---

# fable-mode compatibility adapter

`fable-mode` is a legacy entry name. New behavior belongs to the canonical `get-fable` skill pack and `skills/get-fable/registry.json`.

When the canonical pack is reachable, route there instead of maintaining a second workflow here.

If the host cannot invoke canonical skills directly, preserve these invariants inline:

- route by missing evidence or decision
- resolve repository unknowns and current external facts before they influence architecture
- use bounded plans for broad work and red-green checks for testable behavior changes
- delegate only disjoint work with explicit ownership and acceptance
- treat review, security, release, handoff, evaluation, and recovery as distinct jobs
- advance mutation state after workspace changes
- require fresh current-generation completion evidence after the final mutation
- change the diagnosis before another repair after repeated failure

Evidence types stay narrow: research supports decisions, receipts support execution provenance, handoffs support continuity, and none of them substitutes for behavior verification.

This workflow changes process around a model. It does not change model weights, reproduce a proprietary model, expose hidden reasoning, or guarantee equivalent capability.

Files in this skill

  • aider-fable-rules.md515 B
  • amazon-q-fable-rules.md560 B
  • atlarix-fable-rules.md464 B
  • autogpt-fable-rules.md546 B
  • chatgpt-fable-instruction.md925 B
  • chatgpt-openapi-schema.json2.3 KB
  • claude-code-fable-5.md2.3 KB
  • cline-fable-rules.md535 B
  • codegen-fable-rules.md480 B
  • codex-fable-rules.md1012 B
  • continue-fable-rules.md481 B
  • copilot-fable-instructions.md832 B
  • cursor-fable-rules.mdc854 B
  • deepseek-fable-directive.md552 B
  • devin-fable-instructions.md722 B
  • fable-mode-skill.md1.7 KB
  • fable-spark-directive.md3.9 KB
  • fable5-rules.md3.1 KB
  • grok-bot-directive.md924 B
  • grok-fable-rules.md501 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…