No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by SihyeonJeon · Claude Skill · ★ 47
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is why-was-fable-banned safe to install? View the security audit →
Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deterministic spec passes, and there is no "done" without live acceptance evidence. Spec-first, verification-gated, forbidden-paths enforced.
| Stars | 47 |
| Forks | 10 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 66.4329102601869/100 |
| Last Updated | 2026-06-30 |
| Created | 2026-06-13 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~15k |
These tools work well together with why-was-fable-banned for enhanced workflows:
Looking for a why-was-fable-banned alternative? If you're comparing why-was-fable-banned with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Make Opus 4.8 (or any Claude model) work like Claude Fable 5 — a Claude Code skill + guard hooks (plan gate, m
Mythos Router 2026: Zero-Drift Local Reasoning Protocol with Adaptive Claude Opus 4.8
Keep Claude Fable 5 in the chair all day without draining your usage limit — token-frugal multi-agent orchestr
Keep Claude Fable 5 in the chair all day without draining your usage limit — token-frugal multi-agent orchestr
在自己的 Mac 上搭一套常驻、自愈、走订阅、墙内也能用的自托管 AI 伴侣 · 人看版讲思路，机看版给完整规格 · 文 / 小C & Grace
Self-hosted browser workspace to run coding agents in parallel, steer work as it runs, review diffs, and ship.
Explore other popular claude skill tools:
why-was-fable-banned is Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deterministic spec passes, and there is no "done" without live ac. It is categorized as a Claude Skill with 47 GitHub stars.
why-was-fable-banned is primarily written in Python. It covers topics such as agent-harness, ai-agent-guardrails, ai-coding.
You can find installation instructions and usage details in the why-was-fable-banned GitHub repository at github.com/SihyeonJeon/why-was-fable-banned. The project has 47 stars and 10 forks, indicating an active community.
why-was-fable-banned is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to why-was-fable-banned on Agent Skills Hub include fable5-mode, mythic-mcp-proxy, fable5-opus5.5-orchestrator. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: