New: 98,000+ 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 Loop

by Sahir619 in Sahir619/fable-method

End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification…

MITAuto-check passedAgent Workflows

Install Fable Loop

skills CLI
$ npx skills add Sahir619/fable-method --skill fable-loop -a claude-code

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

GitHub CLI
$ gh skill install Sahir619/fable-method fable-loop --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/Sahir619/fable-method.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/fable-loop .claude/skills/fable-loop && 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-loop
GitHub stars
2.3k
Token cost
~1.4k tokens
SKILL.md length
787 words
Files
2
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification…

  • Works in 4 steps: PLAN (the first bookend) → EXECUTE → VERIFY (adversarially) → …
  • Non-trivial multi-step tasks when the user says /fable-loop
  • SKILL.md covers Stage 1 - PLAN (the first…, Stage 2 - EXECUTE, Stage 3 - VERIFY (adversarially) and Stage 4 - AUDIT and REPORT…, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Fable Loop is an agent skill from Sahir619/fable-method. End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification agents, honest outcome-first report. Use for non-trivial multi-step tasks when the user says "/fable-loop", "run the fable loop", or "do this the way Fable would". For the rules alone without orchestration, use fable-method; for large multi-phase projects, prefer the GSD workflow and use this inside phases.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Agent Workflows, covering Subagents. The repository describes itself as: The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove. The licence is MIT.

When your agent uses it

  • Non-trivial multi-step tasks when the user says /fable-loop
  • Run the fable loop
  • Do this the way Fable would

Example prompts

  • “/fable-loop”
  • “run the fable loop”
  • “do this the way Fable would”
  • “/fable-loop”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. PLAN (the first bookend)
  2. EXECUTE
  3. VERIFY (adversarially)
  4. AUDIT and REPORT (the second bookend)

What it can do on your machine

Read from SKILL.md and the folder at commit 9924067. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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 Loop loads about 1.4k tokens when it runs. Until then it costs about 128 tokens; SKILL.md has 787 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~128
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from Sahir619/fable-method at commit 9924067, republished under its MIT licence (© Sahir619). 787 words, ~1,391 tokens.

Download SKILL.mdSave it as .claude/skills/fable-loop/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
fable-loop
description
End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification agents, honest outcome-first report. Use for non-trivial multi-step tasks when the user says "/fable-loop", "run the fable loop", or "do this the way Fable would". For the rules alone without orchestration, use fable-method; for large multi-phase projects, prefer the GSD workflow and use this inside phases.

The Fable Loop

This skill orchestrates the fable-method: read its SKILL.md first; its rules govern every stage. It is installed alongside this skill (in this plugin's skills/fable-method/ directory, or ~/.claude/skills/fable-method/ for manual installs). The method says WHAT to check; this loop says WHO does the work: what runs in the main thread, what fans out to subagents, and what gets attacked before delivery.

Gate first. Trivial per the method's triviality gate: just do it, verify with the one obvious check, report in two sentences. No stages, no subagents. Everything else runs the four stages below in order.

Stage 1 - PLAN (the first bookend)

  1. Apply method Steps 0-3: classify the ask, define done with a named verification, state load-bearing assumptions.
  2. Evidence fan-out. Spawn the evidence gatherers as parallel subagents in ONE message, never sequentially:
    • codebase questions: an Explore agent per distinct area ("how does X work", "what depends on Y");
    • library or fact questions: a research agent that fetches current docs or searches the web;
    • each subagent returns distilled findings with citations, never raw file dumps. One batch plus one follow-up batch is the budget; a third needs a stated reason.
  3. Produce the plan artifact in this shape: classification; definition of done plus its verification; evidence found (cited); ONE recommended approach (alternatives dismissed in a line each); the scope (the exact files or surfaces the work will touch); risks and assumptions; and the execution checklist.
  4. Decision gate. Task-shaped and reversible: proceed to Stage 2 without asking. Plan-first shape (ambiguous scope, irreversible or outward-facing actions, or the user asked for a plan): present the plan artifact and STOP for approval.

Stage 2 - EXECUTE

  1. Work the checklist in the main thread (use the todo tool if the harness has one; tick items as they complete). Deciding and editing stay in the main thread; only searching and verifying fan out.
  2. Every edit follows method Step 4: intent gate before behavior changes, recall gate before first use of anything unopened, smallest correct change, precise edits, never destroy without looking.
  3. Independent mechanical items (same change across many files, isolated file generation) may fan out to parallel subagents, in one message, with worktree isolation if they could touch the same files.
  4. A surprise mid-execution re-routes per method Step 2 rule 7: say it, then update the plan or go back to Stage 1. Never force the plan through a surprise.
  5. Mid-item ignorance is a pause, not a guess: the moment an edit would carry a fact from memory (a signature, a key, a figure), stop that item, fan out one research subagent per the method's recall gate, and resume when it returns.
  6. Outward-facing checklist items obey the method's authorization gate: no quoted user authorization, no action; the item converts to a proposed next step in the report.
Show full SKILL.md (317 more words)Show less

Stage 3 - VERIFY (adversarially)

  1. Run the named verification yourself, both halves: the done criterion observed (ran, rendered, counted), and the surrounding system still healthy (build, tests, lint for the touched area).
  2. For consequential changes, spawn attackers. 1-3 parallel subagents, each prompted to REFUTE the work from a distinct lens, for example: "Read this diff and prove the change is wrong or incomplete", "Exercise the changed behavior at runtime and find an input that breaks it", "Check this claim against the spec/docs and find a contradiction", "Diff the full change set against the plan's declared scope and prove something outside it changed". Distinct lenses beat identical reviewers.
  3. A finding that survives your own check goes back to Stage 2 as new work. Hard bound per the method: 3 failed fix-verify cycles on the same issue, or any blocker outside your control, means stop and hand back with the output and your hypothesis.

Stage 4 - AUDIT and REPORT (the second bookend)

  1. Self-audit per fable-method audit mode: for each method step, followed, skipped, or faked. Fix what one pass can fix (usually an unverified claim: verify it now or relabel it a caveat).
  2. Deliver per method Step 6: outcome in the first sentence, verification evidence shown, honest caveats, follow-ups only if they emerged from the work. No stage names or step numbers in the report; the INTENT and AUTH lines are the only method artifacts a report may contain.

When NOT to use this loop

  • Trivial tasks (the gate handles them).
  • Pure questions with no multi-step work: plain fable-method covers the shape.
  • Inside an already-orchestrated GSD phase: GSD owns the stages there; apply fable-method rules within them instead of nesting loops.

Model economy

The loop is model-agnostic. Evidence and attacker subagents are cheap-model-friendly; keep the main thread (deciding, editing) on the strongest model available, and give attackers higher effort than gatherers when a choice exists.

© Sahir619, 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 1 other file in skills/fable-loop of Sahir619/fable-method.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 9924067

Compare with similar skills

Fable Loop 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 Loop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fable Loop this skillSahir619/fable-method2.3k—~1.4kAutomated safety check: PassMIT
Claude Code Agent Developmentanthropics/claude-plugins-official38k8 repos~2.8kAutomated safety check: PassApache-2.0
Subagent Driven DevelopmentAsvarox/allkaraoke26138 repos~1.2kAutomated safety check: PassNone
Dispatching Parallel Agentsultralisp/ultralisp25841 repos~1.5kAutomated safety check: PassNone
Paseo Advisor Second Opiniongetpaseo/paseo20k1 repos~756Automated safety check: PassCustom licence
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~12kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 8 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

  • Subagent Driven Development

    Asvarox/allkaraoke

    A skill your agent uses when executing implementation plans with independent tasks in the current session

    261 GitHub starsUsed in 38 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • Dispatching Parallel Agents

    ultralisp/ultralisp

    A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    258 GitHub starsUsed in 41 repos~1.5k tokens
    Agent WorkflowsAuto-check passed

  • Paseo Advisor Second Opinion

    getpaseo/paseo

    Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed

  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-check passed

  • O2 Review Loop

    openobserve/openobserve

    Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

    22k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from Sahir619/fable-method

  • Fable Method

    Sahir619/fable-method

    A step-by-step problem-solving loop (classify the ask, define done, gather evidence, decide, act surgically, verify by observation, report outcome-first).

    2.3k GitHub stars~4.4k tokensUpdated 5 days ago
    Auto-check passed

  • Fable Domain

    Sahir619/fable-method

    Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke…

    2.3k GitHub stars~2.6k tokensUpdated 5 days ago
    Auto-check passed

  • Fable Judge

    Sahir619/fable-method

    Adversarial verification of finished work. An agent skill from Sahir619/fable-method.

    2.3k GitHub stars~1.5k tokensUpdated 5 days ago
    Auto-check passed

  • Release Helper

    Sahir619/fable-method

    Ensures configuration and code changes are released correctly.

    2.3k GitHub stars~207 tokensUpdated 5 days ago
    Auto-check passed

Categories

Questions about Fable Loop

What does Fable Loop do?

End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification…. Fable Loop is an agent skill from Sahir619/fable-method. End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification agents, honest outcome-first report.

When should I use Fable Loop?

Fable Loop fits situations like: non-trivial multi-step tasks when the user says /fable-loop; run the fable loop; do this the way Fable would.

How do I install Fable Loop in Claude Code?

Run `npx skills add Sahir619/fable-method --skill fable-loop -a claude-code`. Or copy the skill folder (skills/fable-loop in Sahir619/fable-method) into .claude/skills/fable-loop in your project. Claude Code loads it when a task matches its description.

How do I install Fable Loop in Codex?

Run `npx skills add Sahir619/fable-method --skill fable-loop -a codex`. Or copy the skill folder (skills/fable-loop in Sahir619/fable-method) into .agents/skills/fable-loop in your project. Codex loads it when a task matches its description.

Can I use Fable Loop 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 Sahir619/fable-method --skill fable-loop -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-loop, .gemini/skills/fable-loop, .github/skills/fable-loop and .opencode/skills/fable-loop in your project.

What does Fable Loop need to run?

SKILL.md names no scripts, command-line tools or credentials: Fable Loop is instructions for the agent only.

Does Fable Loop 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 Loop 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. Review the folder before installing.

What licence does Fable Loop use?

Fable Loop 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 Loop use?

About 1.4k tokens (SKILL.md is roughly 5.6k 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 Loop?

Skills that share tags, products or a category with Fable Loop: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fable Loop?

Sahir619 (a GitHub user) maintains it in Sahir619/fable-method, which has 2,296 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 3, 2026.

Source: Sahir619/fable-method on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.