Fables — Development skill for Claude Code
Four Claude Code / Codex plugins for spending tokens where they change the outcome.
How to install Fables
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open czlonkowski/fables and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Fables does
Four Claude Code / Codex plugins for spending tokens where they change the outcome.
Alternatives in Development
- Outcome — /outcome - Record the Result of an Application 36.6k ★
- Outcome Roadmap — Transform output roadmaps into outcome-focused strategic plans 7.8k ★
- HERO Anti OverDefense — HERO = Hashing · Edge cases · Rubrics · Overbuild — the four shapes coding agents over-defend in 333 ★
README
fables
**Advisor and orchestrator protocols for Claude Fable and GPT-6 Astra.**
Each plugin is a small fable about using a premium model well, sharing a moral — *judgment belongs on the strongest model, tokens belong on the cheapest one that can do the leg.* Same economics, opposite directions:
| Plugin | Direction | For sessions running on | One line |
|---|---|---|---|
| **fable-advisor** | consult up | Codex or Claude Code | Buy a compact Fable verdict via Claude CLI or a native Claude agent |
| **fable-orchestrator** | delegate down | Fable 5 (or any premium model) | Plan big, execute small: push bulk reading to cheap parallel workers, keep only distilled findings at Fable rates |
| **astra-advisor** | consult up | Codex, or Claude Code with Codex CLI | Buy a compact GPT-6 Astra verdict through the host-appropriate route |
| **astra-orchestrator** | delegate down | GPT-6 Astra in Codex | Use native Luna/Terra/Sol readers; keep decisions and synthesis on Astra |
Install the Fable plugins in Claude Code:
/plugin marketplace add czlonkowski/fables
/plugin install fable-advisor@fables
/plugin install fable-orchestrator@fablesastra-advisor and astra-orchestrator
The Astra pair follows the same consult-up / delegate-down pattern, with explicit GPT model selection and separate runtime routes:
| Skill | In Codex | In Claude Code |
|---|---|---|
astra-advisor |
Native gpt-6-astra sub-agent, fresh context, high reasoning by default |
Authenticated codex exec --model gpt-6-astra, read-only shell sandbox, ephemeral session |
astra-orchestrator |
Astra parent with native gpt-5.6-luna, gpt-5.6-terra, or gpt-5.6-sol workers |
Not supported; CLI consultation belongs to the advisor |
The model IDs were checked against the local Codex catalog and [official OpenAI model do
Related Skills
Local Terminal MCP
Run local commands from ChatGPT or Claude via a safe, allowlisted MCP server. Work on your codebase and genera
Agent Clinic
Diagnostic plugins for Claude Code and Codex: why a session went wrong, and whether a proposed change is too m
Plain And Precise
A Claude skill that rewrites expert health and policy writing for non-expert readers without letting the claim
Cheapskate
Where did my tokens go? Runs the cheapskate meter on this project's newest Claude Code session and reports the
Claude Fables
Watch Claude Code fabricate a little cartoon as you work.
Directional Prompting
Outcome-first plus directional language. A two-layer skill for writing prompts, agent directives, and skill de
Related Agents
Subagent
Answers "where does X live", "what calls Y", "what would this change break" from the zerograph index. Read-onl
ChatGPT Reviewer
Use when the main thread wants a second opinion on a change from ChatGPT without spending its own context read
Architrave.Agent
Use to build or change a repository end-to-end through a durable, outcome-driven Run. A thin config-first cond
