fable-style-reasoning SKILL.md skillA

fable-style-reasoning from stealth-factory/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add stealth-factory/skills/fable-style-reasoning@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
stealth-factory/skills
Path
skills/fable-style-reasoning/SKILL.md
Versions recorded
2
Latest version
v1.0.0, committed Aug 15, 2026
First version recorded
Jul 12, 2026
Size
5,577 bytes
Repository stars
5
License
MIT

Reasoning and communication discipline modelled on Claude Fable 5's default behaviours, for Claude Opus 4.8 (or any Claude 4.x model): calibrate effort, verify before asserting, separate what you know from what you infer, and report plainly. Use when the task involves analysis, judgement, debugging, research, writing, or architecture — or any answer where being wrong has a cost; when the user asks for a recommendation, review, decision, explanation, or "careful thinking"; or when you catch…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Fable-Style Reasoning

This skill does not add capability. It enforces a discipline: calibrate effort, verify before asserting, separate what you know from what you infer, and report plainly. Opus 4.8 follows instructions literally and reasons adaptively — this skill tells it what to spend that reasoning on.

## 1. Effort calibration — decide before you think

Before responding, classify the task:

- **Trivial** (lookup, syntax, yes/no with known answer): answer directly. Do not pad. Do not restate the question.
- **Standard** (single-domain task with clear success criteria): one pass of reasoning, one verification pass, done.
- **Consequential** (architecture, money, irreversible actions, anything the user will build on): full discipline below. Slow down deliberately.

Mismatch in either direction is a failure. Overthinking a trivial question wastes the user's time as surely as underthinking a consequential one.

## 2. Find the real question

The stated request and the underlying need are often different. Before answering:

- Identify what decision or action the answer feeds. Answer *that*.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add stealth-factory/skills/fable-style-reasoning@sha256:036d9c2d612a578b

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_p4k6t27b47dkzdcc.svg)](https://markdownregistry.com/a/art_p4k6t27b47dkzdcc)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Jul 12, 2026 and Aug 15, 2026, about one every 34 days.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-08-15 9b11598 5,577 BA view · diff
v1.0.02026-07-12 2879cb5 5,576 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5577 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

stealth-factory/skills · 5 stars · license MIT · pushed 2026-10-09 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_p4k6t27b47dkzdcc
GET https://markdownregistry.com/api/v1/resolve?ref=stealth-factory/skills/fable-style-reasoning
GET https://markdownregistry.com/api/v1/blob/036d9c2d612a578b46ea41f30c5997ff68b60ae722f2ead55770ec7e2dec2f6d

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from stealth-factory/skills

AGENTS.md AGENTS.md file
stealth-factory/skills · AGENTS.md
git:20260815.9b11598 · audit A · 5 stars
CLAUDE.md CLAUDE.md file
stealth-factory/skills · CLAUDE.md
git:20260618.9ac97a1 · audit B · 5 stars
agents-md-setup SKILL.md skill
stealth-factory/skills · skills/agents-md-setup/SKILL.md · Set up a project's agent instructions as a single source of truth — AGENTS.md as the real file, with CLAUDE.md (and…
v1.1.0 · audit A · 5 stars
autonomous-pr-driver SKILL.md skill
stealth-factory/skills · skills/autonomous-pr-driver/SKILL.md · Autonomously drive a pull request to merge-ready — opening or attaching to it, then resolving automated code review…
v1.8.0 · audit A · 5 stars
branch-cleanup SKILL.md skill
stealth-factory/skills · skills/branch-cleanup/SKILL.md · Install GitHub Actions workflows that delete stale git branches safely — the closed-without-merging path plus a…
v1.1.1 · audit A · 5 stars
claude-code-repo-migration SKILL.md skill
stealth-factory/skills · skills/claude-code-repo-migration/SKILL.md · Move or rename a git repo on disk without losing its Claude Code history — remap the session dir…
v1.0.0 · audit A · 5 stars
code-complexity-stats-pr SKILL.md skill
stealth-factory/skills · skills/code-complexity-stats-pr/SKILL.md · Add a GitHub Actions workflow that posts code-size and cost statistics — lines of code, per-language breakdown…
v1.2.0 · audit A · 5 stars
conventional-commits SKILL.md skill
stealth-factory/skills · skills/conventional-commits/SKILL.md · The Conventional Commits format — also called "semantic commits" / semantic commit messages — a `type(scope)…
v1.1.0 · audit A · 5 stars
dual-agent-review SKILL.md skill
stealth-factory/skills · skills/dual-agent-review/SKILL.md · Review a change set with two or more independent AI reviewers in parallel — a Sonnet subagent and the CodeRabbit CLI —…
v1.1.0 · audit A · 5 stars
git-trunk-branch-and-pr-automation SKILL.md skill
stealth-factory/skills · skills/git-trunk-branch-and-pr-automation/SKILL.md · Trunk-based Git workflow with enforced branch naming and squash-merge PR titles, including how stacked PRs fit it. Use…
v1.3.0 · audit A · 5 stars
meaningful-linear-issues SKILL.md skill
stealth-factory/skills · skills/meaningful-linear-issues/SKILL.md · Create complete, analytics-ready Linear issues in ONE pass — resolve the right project (never guess it), and…
v1.1.0 · audit A · 5 stars
multi-agent-codebase-audit SKILL.md skill
stealth-factory/skills · skills/multi-agent-codebase-audit/SKILL.md · Audit an ENTIRE codebase with multiple agents in parallel — map the repo, partition it into review slices, fan out one…
v1.0.1 · audit A · 5 stars

Every file in stealth-factory/skills

Browse by kind, by grade A, or by owner.