New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Fable

by codejunkie99 in codejunkie99/fable-orchestrator

Use the locally authenticated Claude Code Fable 5.1 model only as the orchestrator for a task, then execute implementation with GPT-5.6 Luna or DeepSeek V4 Flash.

MITAuto-check passed

Install Fable

skills CLI
$ npx skills add codejunkie99/fable-orchestrator --skill fable -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install codejunkie99/fable-orchestrator fable --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/codejunkie99/fable-orchestrator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skill/fable .claude/skills/fable && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
fable
GitHub stars
614
Token cost
~1.3k tokens
SKILL.md length
699 words
Files
3 (incl. scripts)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Use the locally authenticated Claude Code Fable 5.1 model only as the orchestrator for a task, then execute implementation with GPT-5.6 Luna or DeepSeek V4 Flash.

  • Works in 8 steps: Read the objective and relevant local… → Build a compact orchestration packet… → Send the packet to scripts/ask_fable.sh.… → …
  • The user invokes $fable
  • SKILL.md covers Invocation, OpenCode Go compatibility, Workflow and Boundaries, plus 1 more section
  • Runs Shell scripts from its folder

What it does

Fable is an agent skill from codejunkie99/fable-orchestrator. Use the locally authenticated Claude Code Fable 5.1 model only as the orchestrator for a task, then execute implementation with GPT-5.6 Luna or DeepSeek V4 Flash. Use when the user invokes $fable or asks Fable to orchestrate Codex agents.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `agents/openai.yaml` and `scripts/ask_fable.sh`).

It works with DeepSeek and OpenAI. The repository describes itself as: Fable 5.1 orchestrates. GPT-5.6 Luna and DeepSeek V4 Flash implement. The licence is MIT.

When your agent uses it

  • The user invokes $fable
  • Asks Fable to orchestrate Codex agents

Example prompts

  • “/fable”

Requirements

  • A Bash shell

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Read the objective and relevant local instructions. Inspect enough of the
  2. Build a compact orchestration packet containing the objective, acceptance
  3. Send the packet to scripts/ask_fable.sh. Use Claude's fable alias; do not
  4. Require a bounded task graph with role, model or agent type, owned files or
  5. Validate the graph against the actual task and current tools. Codex has final
  6. Spawn independent ready nodes in parallel, up to the live collaboration
  7. Collect results, inspect changed files, and run proportionate verification.
  8. Finish only when acceptance criteria and verification pass. Report selected

What it can do on your machine

Read from SKILL.md and the folder at commit e6345e5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Fable loads about 1.3k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 699 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~61
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from codejunkie99/fable-orchestrator at commit e6345e5, republished under its MIT licence (© codejunkie99). 699 words, ~1,321 tokens.

Download SKILL.mdSave it as .claude/skills/fable/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
fable
description
Use the locally authenticated Claude Code Fable 5.1 model only as the orchestrator for a task, then execute implementation with GPT-5.6 Luna or DeepSeek V4 Flash. Use when the user invokes $fable or asks Fable to orchestrate Codex agents.

Fable orchestrator

Claude Fable 5.1 supplies orchestration decisions only. Codex remains the runtime that spawns workers, owns files, runs tools, verifies the result, and reports to the user.

Invocation

Treat everything after $fable as the objective. Fable 5.1 always owns orchestration. Implementation workers are restricted to GPT-5.6 Luna and DeepSeek V4 Flash:

  • $fable build the feature
  • $fable debug this; implementer: gpt-5.6-luna

Model names are requests, not guesses. Before dispatch, inspect the current spawn_agent tool description and custom agent roles. Use only models or roles that are currently callable. If a requested model is unavailable, say so and use the closest available choice only when that substitution is low-risk; otherwise ask for a replacement.

For the simplest automatic path, the user can provide only an objective. Apply this ordered classifier when they did not explicitly choose a route:

  • loop construction, repeated iteration, or high-throughput mechanical work: use a callable OpenCode Go agent pinned to opencode-go/deepseek-v4-flash;
  • implementation: use a callable OpenCode Go agent pinned to opencode-go-responses/gpt-5.6-luna, then opencode-go/deepseek-v4-flash;
  • planning, research, review, and other work: choose by normal task fit.

Prefer an exposed agent_type that pins both model and provider. Never infer callability from a config file or send a raw model override across providers. An explicit implementation choice wins only when it is GPT-5.6 Luna or DeepSeek V4 Flash. Do not assign implementation to any other model. After any applicable approval gate, state only <Agent> — <Model>: <bounded responsibility>, then immediately start. Classify by the callable model pin, not the agent's display name. Do not show the full model catalog unless asked.

OpenCode Go compatibility

Codex Router owns OpenCode Go provider setup, model discovery, and credentials; Fable must not duplicate them. A user adds the OpenCode Go API key once through the router's local secure setup. Never request or paste an API key in chat or store it in a Fable packet. Fable consumes only callable opencode-go/ and opencode-go-responses/ agents supplied by Codex, so it needs no proxy, dashboard, or second static model list. Start a new Codex task after changing the provider or agent definitions.

Show full SKILL.md (356 more words)Show less

Workflow

  1. Read the objective and relevant local instructions. Inspect enough of the workspace to give Fable facts rather than assumptions.
  2. Build a compact orchestration packet containing the objective, acceptance criteria, workspace context, constraints, protected files, evidence already gathered, callable worker menu, concurrency limit, and user preferences.
  3. Send the packet to scripts/ask_fable.sh. Use Claude's fable alias; do not read, copy, print, or modify Claude credentials.
  4. Require a bounded task graph with role, model or agent type, owned files or responsibility, dependencies, expected output, verification, and a stop condition for every node. Reject any implementation node assigned to a model other than GPT-5.6 Luna or DeepSeek V4 Flash. Fable 5.1 adjudication remains outside the worker graph.
  5. Validate the graph against the actual task and current tools. Codex has final responsibility for safety and scope. Do not execute invented models, unsafe actions, or work outside the user's request.
  6. Spawn independent ready nodes in parallel, up to the live collaboration limit. Tell every code-writing worker its ownership and that other agents share the workspace, so it must preserve and accommodate their edits.
  7. Collect results, inspect changed files, and run proportionate verification. For complex work, send a concise results packet back through the helper for the next graph or final adjudication. Cap this at three Fable calls unless the user asks to continue.
  8. Finish only when acceptance criteria and verification pass. Report selected models, material changes, and concrete proof.

Whenever the helper returns Fable's orchestration output, display it verbatim under this exact heading:

text
Fable 5.1 speaks:

Do not relabel ordinary Codex or worker-agent output as Fable speech.

Boundaries

  • Fable plans and adjudicates; it does not silently replace the Codex workers.
  • Exchange decisions, evidence, task packets, diffs, test results, and blockers, not hidden reasoning.
  • Orchestration does not expand authorization. Publishing, deployment, destructive operations, spending, and external messages retain their normal approval boundaries.
  • If delegation adds no value, use one worker or execute directly after the Fable plan.

Calling Fable

Pass the packet as standard input:

bash
printf '%s' "$PACKET" | "$HOME/.codex/skills/fable/scripts/ask_fable.sh"

Do not place secrets in the packet. The helper uses the existing local Claude Code authentication and creates no persistent Claude session.

© codejunkie99, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in skill/fable of codejunkie99/fable-orchestrator.

  • SKILL.md
  • agents/openai.yaml
  • scripts/ask_fable.sh

Open the folder on GitHubat commit e6345e5

Compare with similar skills

Fable next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Fable compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fable this skillcodejunkie99/fable-orchestrator614—~1.3kAutomated safety check: PassMIT
ModLens Image Vision Bridgeliustack/modlens4.1k—~1.3kAutomated safety check: NotesMIT
Adversarial Speczscole/adversarial-spec5561 repos~8.3kAutomated safety check: NotesMIT
Deep Reviewdyad-sh/dyad22k—~1.4kAutomated safety check: PassCustom licence
Dingo VerifyMigoXLab/dingo757—~741Automated safety check: NotesApache-2.0
Remember Learningsdyad-sh/dyad22k—~1.1kAutomated safety check: PassCustom licence

Similar skills

  • ModLens Image Vision Bridge

    liustack/modlens

    Gives text-only models sight by running the modlens CLI on an image path or URL and returning structured JSON evidence with transcribed text, layout and semantics.

    4.1k GitHub stars~1.3k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check: notes

  • Adversarial Spec

    zscole/adversarial-spec

    Iteratively refine a product spec by debating with multiple LLMs (GPT, Gemini, Grok, etc.) until all models agree.

    556 GitHub starsUsed in 1 repo~8.3k tokens
    Product & Project ManagementAuto-check: notes

  • Deep Review

    dyad-sh/dyad

    Deep multi-agent code review run locally — a fleet of parallel finder agents reviews the diff from independent angles, then adversarial verifier agents reproduce each finding before it is reported.

    22k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed

  • Dingo Verify

    MigoXLab/dingo

    A skill your agent uses when the user wants to fact-check an article or verify factual claims in a document.

    757 GitHub stars~741 tokensUpdated 9 days ago
    Data & AnalyticsAuto-check: notes

  • Remember Learnings

    dyad-sh/dyad

    Review the current session for errors, issues, snags, and hard-won knowledge, then update the rules/ files (or AGENTS.md if no suitable rule file exists) with actionable learnings.

    22k GitHub stars~1.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Dingo Verify

    MigoXLab/dingo

    A skill your agent uses when the user wants to fact-check an article or verify factual claims in a document.

    757 GitHub stars~833 tokensUpdated 9 days ago
    AI & LLM EngineeringAuto-check passed

Works with

Questions about Fable

What does Fable do?

Use the locally authenticated Claude Code Fable 5.1 model only as the orchestrator for a task, then execute implementation with GPT-5.6 Luna or DeepSeek V4 Flash. Fable is an agent skill from codejunkie99/fable-orchestrator.6 Luna or DeepSeek V4 Flash.

When should I use Fable?

Fable fits situations like: the user invokes $fable; asks Fable to orchestrate Codex agents.

How do I install Fable in Claude Code?

Run `npx skills add codejunkie99/fable-orchestrator --skill fable -a claude-code`. Or copy the skill folder (skill/fable in codejunkie99/fable-orchestrator) into .claude/skills/fable in your project. Claude Code loads it when a task matches its description.

How do I install Fable in Codex?

Run `npx skills add codejunkie99/fable-orchestrator --skill fable -a codex`. Or copy the skill folder (skill/fable in codejunkie99/fable-orchestrator) into .agents/skills/fable in your project. Codex loads it when a task matches its description.

Can I use Fable in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add codejunkie99/fable-orchestrator --skill fable -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fable, .gemini/skills/fable, .github/skills/fable and .opencode/skills/fable in your project.

What does Fable need to run?

Going by SKILL.md and its folder, Fable needs a shell for the scripts in its folder. Our summary lists: A Bash shell.

Does Fable access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Fable safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Fable use?

Fable is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Fable use?

About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Fable?

Skills that share tags, products or a category with Fable: ModLens Image Vision Bridge (liustack/modlens, 4.1k stars), Adversarial Spec (zscole/adversarial-spec, 556 stars), Deep Review (dyad-sh/dyad, 22k stars) and Dingo Verify (MigoXLab/dingo, 757 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fable?

codejunkie99 (a GitHub user) maintains it in codejunkie99/fable-orchestrator, which has 614 GitHub stars. The repository was last updated on September 4, 2026.

Source: codejunkie99/fable-orchestrator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.