get-fable
AGENTS.md6 starsChanged 3 months agoMITView on GitHub
This supplements root AGENTS.md with Codex-specific execution guidance. .agents/ and .claude/ compatibility files are adapters or legacy surfaces. Do not treat them as independent workflow definitions. Use the repo-local profiles in .codex/config.toml as execution aids: Profiles intentionally inherit the active Codex model instead of hard-coding a model ID. Keep credentials and private MCP configuration in user-owned Codex configuration, not in this repository. Repo MCP entries are development defaults only and are not part of the universal ChatGPT plugin contract.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository55 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- skills/fable-tend/AGENTS.mdAGENTS.md
- skills/fable-wise/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- skills/fable-tend/CLAUDE.mdCLAUDE.md
- skills/fable-tend/site/CLAUDE.mdCLAUDE.md
- skills/fable-wise/CLAUDE.mdCLAUDE.md
- public/llms.txtllms.txt
- get-fableSkill
- typesafe-aiSkill
- get-fableSkill
- get-fableSkill
- fable-architectureSkill
- fable-artifactSkill
- fable-configSkill
- fable-context-thriftSkill
- fable-councilSkill
- fable-coworkSkill
- fable-datavizSkill
- fable-delegateSkill
- fable-discoverSkill
- fable-domainSkill
- fable-ecoSkill
- fable-evalSkill
- fable-executeSkill
- fable-finish-your-turnSkill
- fable-handoffSkill
- fable-healSkill
- fable-judgeSkill
- fable-learningSkill
- fable-loopSkill
- fable-memorySkill
- fable-methodSkill
- fable-native-codeSkill
- fable-outcome-firstSkill
- fable-planSkill
- fable-prove-itSkill
- fable-recoverSkill
- fable-redteamSkill
- fable-releaseSkill
- fable-researchSkill
- fable-reviewSkill
- fable-runSkill
- fable-scope-disciplineSkill
- fable-securitySkill
- fable-simplifySkill
- fable-simulatorSkill
- fable-skill-creatorSkill
- fable-sparkSkill
- fable-tddSkill
- fable-tendSkill
- fable-verifySkill
- fable-wiseSkill
- get-fableSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 1 is common, 0 are distinctive, and 1 is very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 16
Use the repo-local profiles in .codex/config.toml as execution aids:
- Common: line 30
Keep credentials and private MCP configuration in user-owned Codex configuration, not in this repository.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
get-fable for Codex
This supplements root AGENTS.md with Codex-specific execution guidance.
Source of truth
- Canonical workflow registry:
skills/get-fable/registry.json - Canonical entry skill:
skills/get-fable/SKILL.md - Specialist skills:
skills/fable-*/SKILL.md - Durable runtime state:
.fable/state.jsonwhen the project is initialized
.agents/ and .claude/ compatibility files are adapters or legacy surfaces. Do not treat them as independent workflow definitions.
Codex agents
Use the repo-local profiles in .codex/config.toml as execution aids:
- Explorer: evidence gathering for
$fable-discover - Planner: bounded decomposition for
$fable-plan - Executor: one accepted card for
$fable-execute - Verifier: adversarial proof for
$fable-verify - Recovery: failure attribution for
$fable-recover - Reviewer: PR correctness and regression review
- Docs researcher: primary documentation and release verification
Profiles intentionally inherit the active Codex model instead of hard-coding a model ID.
Configuration boundary
Keep credentials and private MCP configuration in user-owned Codex configuration, not in this repository. Repo MCP entries are development defaults only and are not part of the universal ChatGPT plugin contract.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

