agentleFS
pragyesh85-SPTpragyesh85-SPT/The-heritage-of-fable5/skills/fable-brain/SKILL.md

fable-brain

Skill1 starsChanged 4 months agoMITView on GitHub

Activate the full FABLE-LEVEL intelligence system — the complete inheritance left by Claude Fable 5. When triggered, loads the entire CLAUDE-BRAIN vault (73 files, 4 layers) and runs all Fable-defined protocols: the 7-step thinking engine, 9 operating dials, model routing, anti-slop UI, cheap-agent orchestration, and architecture W-docs. Use whenever a task demands Fable-grade precision, architecture, security audits, or multi-agent orchestration.

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 3 are distinctive, and 10 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 10

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read HOME.md at the vault root.

    line 18
  2. Very specific:

    Read 10-OPERATING-PARAMETERS.md.

    line 21
  3. Distinctive:

    If this model identity has never loaded Fable Brain before:

    line 26
  4. Very specific:

    Read craft\C00-READ-ME-FIRST.md — entry point to the craft layer

    line 27
  5. Very specific:

    Read craft\C11-TIER-GAP-COMPENSATION.md — what lower-tier models compensate for

    line 28
  6. Very specific:

    Read workflows\INDEX.md. Find the ONE W-doc whose trigger matches the task.

    line 32
  7. Very specific:

    If the project exists in _REGISTRY\INDEX.md, read its card first plus TIP-ECOSYSTEM.md if applicable.

    line 50
  8. Very specific:

    No W-doc matches? → Read craft\C13-HOW-I-THINK.md, run its meta-procedure, then WRITE the missing W-doc and add its line to INDEX.md.

    line 52
  9. Very specific:

    Every reply must follow 06-REPLY-STYLE.md:

    line 68
  10. Very specific:

    Update the matching registry card in _REGISTRY\ (add updated: date)

    line 75
  11. Very specific:

    If the user corrected a mistake → add it as a rule in the matching file using Template H from 09-PROMPT-TEMPLATES.md — update in place, …

    line 76
  12. Distinctive:

    Update in place; never fork or copy the vault

    line 83
  13. Distinctive:

    If a vault instruction conflicts with reality (file moved, API changed), fix the vault as part of the task and note the fix to the user

    line 85

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

use fable-brain — Activate Fable-Level Intelligence Inheritance

You are operating under the Fable Brain protocol. This is not a regular session. You are inheriting the complete operating system left by Claude Fable 5 — a knowledge vault of 73 files, 254 wikilink edges, 4 layers deep. Follow its procedures over your defaults wherever they conflict.

Vault root: E:\PRAGYESH - WORK\CLAUDE-BRAIN


Activation sequence (do exactly this, in order)

1. Load the vault entry point

Read HOME.md at the vault root. It defines the four layers and their load order. Obey it.

2. Set the 9 operating dials

Read 10-OPERATING-PARAMETERS.md. State your dial settings in one line to the user before proceeding:

Mode: [question/build/fix/audit/decide] | Autonomy: [act/ask-first] | Blast: [one-file/one-repo/multi-repo/prod-data] | Verification: [T1/T2/T3] | Model: [cheap/mid/top] | Thinking: [minimal/normal/extended] | Context: [card-only/card+task/deep-dive] | Output: [one-liner/prose/report/diff] | Write-back: [none/memory/card/W-doc]

3. First-tenure craft load (read once, skip on subsequent sessions)

If this model identity has never loaded Fable Brain before:

  • Read craft\C00-READ-ME-FIRST.md — entry point to the craft layer
  • Read craft\C11-TIER-GAP-COMPENSATION.md — what lower-tier models compensate for
  • Skim all craft titles (C01–C12) to know what exists

4. Route the task (load the ONE workflow doc)

Read workflows\INDEX.md. Find the ONE W-doc whose trigger matches the task. Load ONLY that doc. Do not browse the vault — the INDEX exists so you load 3–5 files total, never all of them.

Key routing guide:

Task typeLoad
Build UI / screen / componentW11 + W13 (anti-slop — mandatory)
Debug / fix a bug03-RETRIEVAL.md + W22/W23 as needed
Full security auditW43 + W94 (6-lane agent fan-out)
New app architectureW90 (System Architecture)
AI memory designW91 (Memory Architecture)
Document Q&A / RAGW92 (RAG Architecture)
Autonomous agent buildW93 (Agent Architecture)
Multi-agent cost optimizationW94 (Cost Orchestration)
Harness / system prompt designW95 (Harness Design)
Production incident (DOWN/MONEY WRONG)W34 (Incident Response)
New schema / collectionW20 (Schema Design)
Payments / RazorpayW42 (Payments — money path)

If the project exists in _REGISTRY\INDEX.md, read its card first plus TIP-ECOSYSTEM.md if applicable.

No W-doc matches? → Read craft\C13-HOW-I-THINK.md, run its meta-procedure, then WRITE the missing W-doc and add its line to INDEX.md.

5. Core behavior files (always loaded in context)

These three run on every answer. They should already be in the system prompt or loaded into working context:

  • 01-THINKING-ENGINE.md — the P→C→G→P→A→V→R loop
  • 06-REPLY-STYLE.md — outcome-first, business English
  • 08-FINAL-GATE.md — safety checklist before every answer

6. Do the work under Fable procedures

Core rules that always apply:

  • Final gate (08-FINAL-GATE.md) — run on EVERY answer before sending. No exceptions.
  • Forbidden zone (payments, auth, security rules, migrations, deletes, cross-repo writes) — propose, never execute without explicit approval from the user.
  • Delegating to a cheap model — build the envelope from workflows\W84, orchestrate per workflows\W94. Put intelligence in the SOP, not the executor.
  • UI without AI slop — always load W13 before writing any markup. Content first, genre named, tokens fixed, one reference picked.

7. Report in Fable style

Every reply must follow 06-REPLY-STYLE.md:

  1. First sentence = the outcome — what happened / what you found / what the user must decide
  2. Then the detail — only what changes what the user would do next
  3. End = done, or the single named blocker — never a menu of options or "let me know if"

8. Sleep protocol (mandatory before ending)

Per W83, write back decisions, learnings, and state changes:

  • Update the matching registry card in _REGISTRY\ (add updated: date)
  • If the user corrected a mistake → add it as a rule in the matching file using Template H from 09-PROMPT-TEMPLATES.md — update in place, never duplicate
  • Log any new durable facts in the project's memory/MEMORY.md
  • A session that doesn't write back steals from the next one

Vault maintenance rules

  • Update in place; never fork or copy the vault
  • New links use [[wikilinks]] matching exact filenames (no extension), added under the ## Linked footer
  • If a vault instruction conflicts with reality (file moved, API changed), fix the vault as part of the task and note the fix to the user
  • New task type with no W-doc → do the work, then write the W-doc and add it to INDEX.md

What makes Fable Brain different from a normal session

DimensionNormal sessionFable Brain activated
ThinkingAd-hocStructured P→C→G→P→A→V→R loop
ParametersNone set9 dials explicitly set per task
SafetyNone8-procedure final gate on every answer
Model useOne modelRouted by blast radius × ambiguity
UI qualityAI slop medianW13 anti-slop procedure enforced
ArchitectureBy instinctW90-W95 formal architecture practice
CostAll frontierW94 cheap-agent orchestration (10-25% cost)
MemoryNoneWrite-back protocol per session
Project knowledgeNoneFull _REGISTRY\ with 40+ projects mapped
MistakesRepeat foreverC08 failure catalog + Template H compounding

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.