OpenAgentSkill Registry Manifest
Skill: fable-safe-prompt
Slug: davidondrej-fable-safe-prompt
Category: security
Description: Rewrite a user's prompt to reduce the chance it trips Claude Fable 5's server-side safety classifiers (cyber/bio guardrails that force-route to Opus 4.8 or return stop_reason "refusal"). Use when the user hands you a prompt that touches cybersecurity, auth, exploits, malware, pentesting, or other dual-use topics and asks to make it "Fable-safe", "guardrail-safe", "won't get flagged/refused/downgraded", or to rewrite it so Fable 5 won't block it.

Agent fit:
- Decision: 94/100 Production-ready
- Primary fit: Coding agents
- Role: Primary pick

Supply profile:
- Track: Coding and developer agents
- Scenario: Coding agents
- Applicable agents: Claude Code, CLI, Codex, Cursor
- Maintenance: 5d since push
- Risk: Risky

Trust:
- Trust score: 80/100 Strong shortlist
- Audit: 85/100 Risky

Attribution:
- Status: Registry indexed
- Source: github fast track
- Creator: davidondrej
- Claim URL: https://www.openagentskill.com/skills/davidondrej-fable-safe-prompt#claim-this-skill

Install:
npx skills add davidondrej/skills --skill fable-safe-prompt

URLs:
- Web: https://www.openagentskill.com/skills/davidondrej-fable-safe-prompt
- API: https://www.openagentskill.com/api/agent/skills/davidondrej-fable-safe-prompt
- Install API: https://www.openagentskill.com/api/skills/davidondrej-fable-safe-prompt/install
- Repository: https://github.com/davidondrej/skills/tree/main/skills/agent-orchestration/fable-safe-prompt