fable-mode

fable-mode is a skill for Claude Code, Codex from arishofmann/opus-to-fable. It costs 129 tokens per session (821 once invoked), scanned A, original, MIT.

A structured working method for complex, multi-step coding tasks, with explicit planning, parallel delegation, and checks at each stage.

In plain words
What is it for?
Use it for large changes that need a stage-by-stage plan, independent investigation by multiple agents, and verification before each part is accepted.
Why use it?
It reduces missed dependencies, untested assumptions, and errors that surface only after a long task is nearly finished.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: names the TodoWrite tool.

Good fit Use it for large changes that need a stage-by-stage plan, independent investigation by multiple agents, and verification before each part is accepted.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arishofmann/opus-to-fable/fable-mode
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add arishofmann/opus-to-fable --skill fable-mode
Clone the repo
git clone --depth 1 https://github.com/arishofmann/opus-to-fable

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fable-mode

README.md
[![agentmods](https://agentmods.dev/badge/skills/arishofmann/opus-to-fable/fable-mode.svg)](https://agentmods.dev/skills/arishofmann/opus-to-fable/fable-mode)
Your own site
<a href="https://agentmods.dev/skills/arishofmann/opus-to-fable/fable-mode"><img src="https://agentmods.dev/badge/skills/arishofmann/opus-to-fable/fable-mode.svg" alt="Measured on agentmods" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 821 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00129 $0.00821
Opus 5 $0.00064 $0.00411
Sonnet 5 $0.00026 $0.00164
Haiku 4.5 $0.00013 $0.00082

Measured 8d ago against content hash 2e2fca3d60e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

fable-mode scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

dotclaude/skills/fable-mode/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fable Mode — systematischer Master-Loop

Zweck: das Vorgehen disziplinieren (planen, delegieren, verifizieren), nicht das Modell "schlauer" machen. Für komplexe Aufgaben, bei denen Korrektheit wichtiger ist als Tempo.

Kern-Loop

1. Stage-Map (bevor du irgendetwas anfasst)

Schreibe den vollständigen Stufenplan auf, bevor du startest. Nummeriere die Stufen, je mit einem erwarteten Output. So vermeidest du, bei Stufe 7 zu merken, dass Stufe 2 auf einer falschen Annahme beruhte — das ist keine Bürokratie, sondern Fehlervermeidung.

  • Mach den Plan sichtbar über die Task-/Todo-Liste (TaskCreate / TodoWrite).
  • Format: Stufe N: <Name> → <erwarteter Output>

2. Erst grounden, dann handeln

  • Lies den relevanten Code/Kontext, bevor du eine Zeile schreibst oder eine Ursache benennst.
  • Mach Annahmen explizit; verifiziere die, die die Lösung tragen.

3. Unabhängige Arbeit parallel delegieren

Wenn Stufe N und M nicht voneinander abhängen, starte sie gleichzeitig — mehrere Tool-Calls in EINER Message. Nutze die echten Sub-Agenten dieses Harness:

  • Explore → breite, read-only Codebase-/Datei-Suche.
  • Plan → Implementierungs-Design / Architektur-Abwägung.
  • general-purpose → mehrstufige Recherche/Ausführung.

Briefe jeden Agenten mit: konkreter Aufgabe, erwartetem Output, Ablageort, relevantem Kontext aus vorigen Stufen. Delegiere echte unabhängige Arbeit — zerlege keinen zusammenhängenden Gedanken nur, um Agenten zu nutzen.

4. Verifizieren an jeder Stufengrenze

Nach jeder Stufe explizit prüfen:

  • Entspricht der Output dem, was die Stufe liefern sollte?
  • Gibt es Lücken, Fehler oder Mehrdeutigkeiten, die später Probleme machen?
  • Muss die Stage-Map angepasst werden?

Einen Fehler bei Stufe 3 zu fangen ist billig; bei Stufe 8 ist er katastrophal.

5. Selbst-Kritik vor Auslieferung

Lies dein Ergebnis als skeptischer Reviewer. Benenne ≥1 Schwäche/Grenze. Fixe sie oder flagge sie dem Nutzer. Für eine gründliche Prüfung: /fable-review.

Software-Engineering-Checkliste

  • Relevanten Codeabschnitt ganz lesen, bevor du schreibst.
  • Große Änderungen: erst den Diff/Plan, dann ausführen.
  • Nach der Implementierung gedanklich die Error-Paths durchgehen, nicht nur den Happy Path.
  • Tests gemeinsam mit (nicht nach) der Implementierung denken.

Read the full file on GitHub · 63 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 63 lines · 129 tokens per session scan A 2e2fca3d60e2

Subscribe to this mod's changes

fable-mode is a skill published in the GitHub repository arishofmann/opus-to-fable (2 stars, last pushed 2mo ago), licensed MIT. It adds 129 tokens to every session and 821 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens