llms.txt git:20261020.a2aa9efA

Immutable. This exact content never changes and is served at /api/v1/blob/c4a7a209032ee7cd.

# Fable-5 for Codex

Fable-5 is a local Codex completion-verification plugin, retaining audits, reviews, fact checks, understanding, design options and sweeps. The unreleased 0.5 source adds requirement-mapped evidence and stale-aware handoffs.

Latest public tagged release: `v0.4.0-alpha.2`.

```powershell
npx github:rhein1/fable5-codex#v0.4.0-alpha.2
codex plugin add fable5-codex@personal
```

Source skills (the tagged alpha.2 release does not include fable-verify):

- `$fable-audit`
- `$fable-verify`
- `$fable-deep-review`
- `$fable-fact-check`
- `$fable-understand`
- `$fable-design-options`
- `$fable-sweep`

Fable requires source-backed evidence, explicit unknowns and truthful traces. Model profiles are centralized and resolved against the chosen client's catalog; explicit overrides and fallbacks remain visible. Preferences do not establish account access or actual execution. Quick verification avoids unnecessary workers; all claimed subagents require actual runtime IDs.

Docs:

- README: https://github.com/rhein1/fable5-codex#readme
- Install: https://github.com/rhein1/fable5-codex/blob/main/docs/codex-install.md
- Method: https://github.com/rhein1/fable5-codex/blob/main/docs/method.md
- Development recipes (development branch/main, not the tagged alpha.2 release): https://github.com/rhein1/fable5-codex/blob/main/docs/development-prompts.md
- Optional Laya playbook-selection experiment (source-only, default-off, not the tagged alpha.2 release): https://github.com/rhein1/fable5-codex/blob/main/docs/laya-workflow-selector.md
- Evidence-preserving context packer (source-only; explicit approved inputs, no automatic compaction): https://github.com/rhein1/fable5-codex/blob/main/docs/context-packing.md
- Examples: https://github.com/rhein1/fable5-codex/tree/main/examples/gallery
- Benchmarks and limitations: https://github.com/rhein1/fable5-codex/blob/main/benchmarks/README.md

Boundary: subagents may research and verify, but the main agent owns edits, commits, pushes, reviews, deploys, publication, credentials, and money or wallet actions.