Fable fact check

Skill rhein1/fable5-codex/plugins/fable5-codex/skills/fable-fact-check

OpenAI Codex plugin for evidence-first code review, audits, fact checks, run contracts, and bounded subagent workflows.

Install

npx -y skills add rhein1/fable5-codex --skill fable-fact-check

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Claim-by-claim verification of docs, status reports, launch claims, changelogs, READMEs, runbooks, and "done/tested/working/live" assertions against source, tests, artifacts, and runtime evidence. Use when the user asks Codex to fact-check, verify claims, audit truthfulness, or compare docs to reality.

SKILL.md

2.6 KB, as published. Nobody here has run it

Fable Fact Check

Verify claims against actual evidence. Do not edit claims unless the user asks for a correction pass.

For ECF-style governed runs, use ../../references/ecf-run-contract.md. For large or high-risk fact checks, use real Codex subagents when the runtime exposes a subagent tool and the user has not opted out; treat multi-document, launch/status, security/privacy/money/data/API, release-readiness, or many-claim checks as large by default. Otherwise run single-agent multi-lens and say why no subagents were used.

For large or high-risk Fable tasks, recommend running the parent task on gpt-5.6-sol with Ultra (model_reasoning_effort = "ultra") when available. Ultra may delegate proactively, but still explicitly request parallel delegation for disjoint Fable lenses when the runtime supports subagents; otherwise use single-agent multi-lens and report the reason.

Workflow

Identify the document, status report, or claim set.
Restate authority boundaries and declare the ECF run mode: multi-agent only with real spawned subagents, otherwise single-agent multi-lens.
Extract checkable claims. Prioritize words like done, shipped, live, tested, working, complete, supports, secure, verified, deployed, public, and automated.
For each claim, find the implementing source, tests, artifacts, deployment config, or runtime surface that would make it true.
Classify each claim:
- true
- false
- partial
- stale
- unverifiable
Cite exact evidence for every classification.
Separate docs/source mismatch from environment/tooling failure.
If asked to fix docs, patch only the claims that evidence disproves or bounds.

Evidence Safety

Never print raw secrets, tokens, private keys, wallet keys, credential files, or .env values. Redact secret-like values and cite only the file/path/key name needed to explain the issue.

Output

Use a compact table when many claims are checked:

Claim | Verdict | Evidence | Correction

End with the highest-risk false or partial claims and the safest next verification step.

Include a compact Workflow Trace with mode, ECF contract status, lenses covered, spawned agents or no-subagent reason, verification method, and coverage gaps.