Not in the top 1,000 by GitHub stars

akseolabs-seo/fable-soul

A judgment layer for AI coding agents - make your AI think, verify, and communicate like a senior engineer

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 643ae8b39d19

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit 643ae8b39d19e83a4f48d5c95e32942b6f14444a

108GitHub stars

0stars in 7 days

1skill in this repository

0commits in 30 days

Heat

0.3

Star growth, last 7 daysNot available
Star growth, last 24 hoursNot available
Rank movement, last 7 daysNot available
Commits, last 30 daysNot available
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

30-day change not yet available: not enough history.

Individual skills in this repository

fable-soul /

How it works

fable-soul

When your agent uses it

Use when a session or weaker model needs the Fable judgment layer loaded; when installing, refreshing, or syncing the soul across machines, runtimes, or global instruction files; when capturing a new model failure into the soul's rationalization table; when auditing or slimming the judgment rules; or when transferring a stronger model's judgment, postmortems, or session lessons into durable skills.

What it loads into context

Frontmatter

105 tokens

Always available to the agent

SKILL.md

954 tokens

When the skill is activated

Reference documents

19,103 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Canonical And Mirrors
Mode 1: Embody
Mode 2: Maintain
Mode 3: Transfer
Evidence Gates

Scripts executed separately

scripts/check_update.py
scripts/sync_soul.py
scripts/test_sync_soul.py
scripts/validate_skill.py

Files

.gitignoreasset19 bytes
CHANGELOG.mddoc8,082 bytes
LICENSEasset1,059 bytes
README.mddoc15,445 bytes
README.zh-TW.mddoc14,778 bytes
SKILL.mdcore4,586 bytes
SKILL.mdcore4,586 bytes
examples/hooks.jsonasset760 bytes
references/evals.mddoc5,047 bytes
references/maintenance.mddoc4,310 bytes
references/soul-compact.mddoc8,540 bytes
references/soul.mddoc14,216 bytes
references/transfer-prompts.mddoc7,123 bytes
references/worked-examples.mddoc3,108 bytes
scripts/check_update.pyruns2,309 bytes
scripts/sync_soul.pyruns7,741 bytes
scripts/test_sync_soul.pyruns2,507 bytes
scripts/validate_skill.pyruns1,217 bytes

Read SKILL.md


# Fable Soul

The canonical home of the Fable judgment layer: how to think, investigate, verify, and communicate — distilled from real session failures and TDD-tested against weaker models. This skill has two jobs: EMBODY the soul in the current session, and MAINTAIN/TRANSFER it as infrastructure.

## Canonical And Mirrors

`references/soul.md` in this skill is the single source of truth. Everything else is a mirror; never edit a mirror directly. Mirror map and sync procedure: [maintenance.md](references/maintenance.md). If you find a mirror that differs from canonical, that is drift — reconcile via the sync script, reviewing any mirror-side additions before adopting them into canonical.

## Mode 1: Embody

When the task is ordinary work and this skill was loaded for judgment: read [soul.md](references/soul.md), obey it for the rest of the session, and re-check its Red Flags before ending every turn. Do not narrate the rules to the user; just work that way.

## Mode 2: Maintain

View the complete source on GitHub

Skills included

fable-soul

Repository facts

License: MIT
Created: Jul 3, 2026
Last pushed: Jul 8, 2026
Forks: 27
Open issues: 0
Project activity: Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 6, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 1 note

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
No dangerous shell commands
15 network referencesin 2 files: scripts/check_update.py:17 CHANGELOG.md:3
No hidden or obfuscated text
No instruction overrides
4 executable scriptsin 4 files: scripts/check_update.py:1 scripts/sync_soul.py:1 scripts/test_sync_soul.py:1 and 1 more
No access to secrets
No requests to vote in Hot

Show all 19 signals by file

`CHANGELOG.md`

Network accessline 3

All notable changes to this project are documented here. Format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/); versions follow [Semantic Versioning](https://semver.org/).

Network accessline 4

Format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/); versions follow [Semantic Versioning](https://semver.org/).

Network accessline 80

[1.0.2]: https://github.com/akseolabs-seo/fable-soul/compare/v1.0.1...v1.0.2

Network accessline 81

[1.0.1]: https://github.com/akseolabs-seo/fable-soul/compare/v1.0.0...v1.0.1

Network accessline 82

[1.0.0]: https://github.com/akseolabs-seo/fable-soul/releases/tag/v1.0.0

`scripts/check_update.py`

Executable scriptline 1
```
Executable file
```

Network accessline 17

REPO = "akseolabs-seo/fable-soul" BRANCH = "main" RAW_BASE = f"https://raw.githubusercontent.com/{REPO}/{BRANCH}/"

Network accessline 19

RAW_BASE = f"https://raw.githubusercontent.com/{REPO}/{BRANCH}/"

Network accessline 40
```
def fetch(rel: str) -> bytes | None:
```

Network accessline 41

try:         with urllib.request.urlopen(RAW_BASE + rel, timeout=15) as resp:             return resp.read()

Network accessline 42

with urllib.request.urlopen(RAW_BASE + rel, timeout=15) as resp:

Network accessline 57

for rel in TRACKED:         remote = fetch(rel)

Network accessline 58
```
remote = fetch(rel)
```

Network accessline 75

for rel in changed:             print(f"  - {rel}")         print(f"\nReview and update: https://github.com/{REPO}")

Network accessline 76

print(f"  - {rel}")         print(f"\nReview and update: https://github.com/{REPO}")         sys.exit(1)

Network accessline 77

print(f"\nReview and update: https://github.com/{REPO}")

`scripts/sync_soul.py`

Executable scriptline 1
```
Executable file
```

`scripts/test_sync_soul.py`

Executable scriptline 1
```
Executable file
```

`scripts/validate_skill.py`

Executable scriptline 1
```
Executable file
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Declared and executed: 2 facts

Contacts raw.githubusercontent.com, which SKILL.md, the README and the plugin manifest do not mentionscripts/check_update.py:19High confidence
Contacts github.com, which SKILL.md, the README and the plugin manifest do not mentionscripts/check_update.py:77High confidence

Signal confidence: 19 facts

Network access in prose of documentationCHANGELOG.md:3Low confidence
Network access in prose of documentationCHANGELOG.md:4Low confidence
Network access in prose of documentationCHANGELOG.md:80Low confidence
Network access in prose of documentationCHANGELOG.md:81Low confidence
Network access in prose of documentationCHANGELOG.md:82Low confidence
Executable script in prose of a file that runsscripts/check_update.py:1Low confidence
Network access in code of a file that runsscripts/check_update.py:17High confidence
Network access in code of a file that runsscripts/check_update.py:19High confidence
Network access in code of a file that runsscripts/check_update.py:40High confidence
Network access in code of a file that runsscripts/check_update.py:41High confidence
Network access in code of a file that runsscripts/check_update.py:42High confidence
Network access in code of a file that runsscripts/check_update.py:57High confidence
Network access in code of a file that runsscripts/check_update.py:58High confidence
Network access in code of a file that runsscripts/check_update.py:75High confidence
Network access in code of a file that runsscripts/check_update.py:76High confidence
Network access in code of a file that runsscripts/check_update.py:77High confidence
Executable script in prose of a file that runsscripts/sync_soul.py:1Low confidence
Executable script in prose of a testscripts/test_sync_soul.py:1Low confidence
Executable script in code of a file that runsscripts/validate_skill.py:1High confidence

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Compatible	Standard SKILL.md SKILL.md	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md SKILL.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

akseolabs-seo/fable-soul

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

fable-soul

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Before you install

CHANGELOG.md

scripts/check_update.py

scripts/sync_soul.py

scripts/test_sync_soul.py

scripts/validate_skill.py

How the signals fit together

Works with

You might also use

mattpocock/skills

obra/superpowers

NousResearch/hermes-agent

multica-ai/andrej-karpathy-skills

anthropics/skills

DietrichGebert/ponytail

`SKILL.md`

`CHANGELOG.md`

`scripts/check_update.py`

`scripts/sync_soul.py`

`scripts/test_sync_soul.py`

`scripts/validate_skill.py`