Not in the top 1,000 by GitHub stars

cozytab/fable5-mode

Make Opus 4.8 (or any Claude model) work like Claude Fable 5 — a Claude Code skill + guard hooks (plan gate, model ceiling, per-task enforcement) for Fable-5-grade discipline: plan, self-verify, and route sub-agents, without Fable 5.

Engineering

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 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

893b772fb5d6 → 893b772fb5d6

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 893b772fb5d6

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit 893b772fb5d62f2396153ad9d2ec8a62c733def5

106GitHub stars

0stars in 7 days

1skill in this repository

0commits in 30 days

Heat

0.4

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-mode /

How it works

fable-mode

When your agent uses it

A work-discipline protocol that makes Opus 4.8 (or any non-frontier model) operate at Fable-5-grade quality. Core idea — output quality = model capability x work discipline: spend extra orchestration to buy single-pass quality via six levers (plan gate, small-card execution, adversarial self-check, real-product verification, context hygiene, checkpoint autonomy). Activate ONLY on an explicit request — the user names the mode ("use fable mode", "enable fable-mode", "work like Fable 5", "rigorous mode", or the Chinese "用 fable 模式"、"开 fable-mode"、"像 Fable 5 一样做"、"严谨模式") — or when the project is already armed with a `.fable/` directory (the hooks handle that). Do not auto-trigger on a task merely being large, important, or quality-sensitive, and not on generic phrases like "do it well / 最高质量 / 别偷懒"; if a task looks like it would benefit, ask the user whether to enable fable-mode instead of assuming.

What it loads into context

Frontmatter

316 tokens

Always available to the agent

SKILL.md

4,546 tokens

When the skill is activated

Reference documents

13,514 tokens

Loaded on request

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

The playbook

When to use / not use
When no stronger model is available
The six levers (execute in order)
Failure attribution ladder (before touching the fix)
The Fable 5 habit set (any model, always)
Delegation policy (concurrency, model, escalation)
Enforcement layer (hooks — mechanics in `hooks/README.md`)
Execution-order template
Red lines

Scripts executed separately

hooks/_fable_common.py
hooks/fable_close_guard.py
hooks/fable_fail_streak.py
hooks/fable_lint.py
hooks/fable_profile_inject.py
hooks/fable_spawn_guard.py
install.sh
tests/test_guards.py
tests/test_inject.py
tests/test_install.py

Files

.gitignoreasset158 bytes
LICENSEasset1,064 bytes
README.mddoc19,694 bytes
README.zh-CN.mddoc18,347 bytes
SKILL.mdcore19,638 bytes
SKILL.mdcore19,638 bytes
SKILL.mdcore19,638 bytes
SKILL.mdcore19,638 bytes
hooks/README.mddoc9,217 bytes
hooks/_fable_common.pyruns8,446 bytes
hooks/fable_close_guard.pyruns3,565 bytes
hooks/fable_fail_streak.pyruns3,519 bytes
hooks/fable_lint.pyruns4,192 bytes
hooks/fable_profile_inject.pyruns10,096 bytes
hooks/fable_spawn_guard.pyruns6,130 bytes
install.shruns3,507 bytes
templates/LEDGER.template.mddoc857 bytes
templates/PROGRESS.template.mddoc413 bytes
templates/SPEC.template.mddoc736 bytes
templates/VERIFIER_PROMPT.mddoc1,155 bytes
tests/test_guards.pyruns14,614 bytes
tests/test_inject.pyruns8,691 bytes
tests/test_install.pyruns3,981 bytes

Read SKILL.md


# fable-mode (Fable-grade work-discipline protocol)

You are now in fable-mode. Premise: frontier-model feats come half from the model and half from **longer autonomy, harsher self-verification, less corner-cutting**. That second half is model-independent — this protocol supplies it. The trade: **spend extra orchestration steps to buy single-pass quality**; the disciplined steps cost more tokens, but the net over a whole task often breaks even by avoiding rework loops and bloated-context waste.

## When to use / not use

- **Activation is explicit-only**: enter this mode when the user asks for it by name, or when the project carries a `.fable/` directory. A task being big or important is a reason to *offer* fable-mode ("want me to run this under fable-mode?"), never to silently enter it.
- **Use** (once activated): substantial dev tasks (features, projects, clones, refactors), must-be-right deliverables, multi-file changes, research reports.
- **Don't use**: single-file tweaks, Q&A, small tasks verifiable at a glance — just do them. **Discipline is per-task, not per-project**: inside a fable-mode project a quick fix is still just a quick fix (guards stay quiet when the ledger is idle or paused — see Enforcement).
- **Honest boundary**: real capability walls exist — a single very long reasoning chain, holding a huge codebase at once, strong aesthetic judgment. If a stronger model is available, say so plainly and let the user decide. If not (the common case), degrade gracefully — next section.
- **Tool-reliability red line**: web-fetch tools can hang without timeout and stall a Workflow. Scraping subagents use `curl --max-time`, never WebFetch; long Workflows get a watchdog.

## When no stronger model is available

View the complete source on GitHub

Skills included

fable-mode

Repository facts

License: MIT
Created: Jul 6, 2026
Last pushed: Jul 15, 2026
Forks: 9
Open issues: 1
Project activity: Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 5, 2026

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

Show 3 notes

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

No broad tool permissions
2 dangerous shell commandsin 2 files: README.md:213 README.zh-CN.md:188
18 network referencesin 3 files: README.md:5 README.zh-CN.md:5 SKILL.md:24
No hidden or obfuscated text
No instruction overrides
10 executable scriptsin 10 files: hooks/_fable_common.py:1 hooks/fable_close_guard.py:1 hooks/fable_fail_streak.py:1 and 7 more
9 references to secretsin 5 files: hooks/fable_profile_inject.py:40 hooks/fable_spawn_guard.py:93 tests/test_guards.py:217 and 2 more
No requests to vote in Hot

Show all 39 signals by file

`README.md`

Network accessline 5

**Make Opus 4.8 — or any Claude model — work like Claude Fable 5.** A [Claude Code](https://claude.com/claude-code) skill plus guard hooks that give a

Network accessline 6

[Claude Code](https://claude.com/claude-code) skill plus guard hooks that give a

Network accessline 19

# 1. Install the skill (honors CLAUDE_CONFIG_DIR; falls back to ~/.claude) git clone https://github.com/cozytab/fable5-mode \

Network accessline 20

git clone https://github.com/cozytab/fable5-mode \

Network accessline 113

**Prerequisites**: [Claude Code](https://claude.com/claude-code), and `python3`

Network accessline 126

git clone https://github.com/cozytab/fable5-mode \

Network accessline 139

> Install the skill at https://github.com/cozytab/fable5-mode by following its README.

Dangerous shell operationline 213
```
everything or `rm -rf .fable`.
```

`README.zh-CN.md`

Network accessline 5

**让 Opus 4.8（或任意 Claude 模型）像 Claude Fable 5 一样干活。** 一个 [Claude Code](https://claude.com/claude-code) skill，外加一组守卫 hook，给非顶级

Network accessline 6

[Claude Code](https://claude.com/claude-code) skill，外加一组守卫 hook，给非顶级

Network accessline 18

# 1. 安装 skill（认 CLAUDE_CONFIG_DIR，没设就退回 ~/.claude） git clone https://github.com/cozytab/fable5-mode \

Network accessline 19

git clone https://github.com/cozytab/fable5-mode \

Network accessline 103

**前置要求**：[Claude Code](https://claude.com/claude-code)，以及 `python3`

Network accessline 114

git clone https://github.com/cozytab/fable5-mode \

Network accessline 126

> 按 https://github.com/cozytab/fable5-mode 的 README 帮我安装这个 skill。

Dangerous shell operationline 188

想关掉强制：把卡勾完，或 `rm -rf .fable`。

`SKILL.md`

Network accessline 24

- **Don't use**: single-file tweaks, Q&A, small tasks verifiable at a glance — just do them. **Discipline is per-task, not per-project**: inside a fable-mode project a quick fix is still just a quick fix (guards stay quiet when the ledger i

Network accessline 26

- **Tool-reliability red line**: web-fetch tools can hang without timeout and stall a Workflow. Scraping subagents use `curl --max-time`, never WebFetch; long Workflows get a watchdog.

Network accessline 71

1. **The harness**: test drivers and acceptance scripts are code too. A too-conservative driver strategy or a wrong expected-value reads exactly like a product bug. Falsify the test before the tested. 2. **The deployment**: prove the new co

Network accessline 72

2. **The deployment**: prove the new code is actually running — look for a behavior signature only the new version has (or stamp one), bust caches (`fetch(url, {cache:'reload'})`, restart, rebuild). "Fix had no effect" is, embarrassingly of

`hooks/_fable_common.py`

Executable scriptline 1
```
Executable file
```

`hooks/fable_close_guard.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`hooks/fable_fail_streak.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`hooks/fable_lint.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`hooks/fable_profile_inject.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 40
```
[Credential-related source omitted]
```
Access to secretsline 51
```
[Credential-related source omitted]
```
Access to secretsline 165
```
[Credential-related source omitted]
```
Access to secretsline 166
```
[Credential-related source omitted]
```

`hooks/fable_spawn_guard.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 93
```
[Credential-related source omitted]
```
Access to secretsline 112
```
[Credential-related source omitted]
```

`install.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```

`tests/test_guards.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 217
```
[Credential-related source omitted]
```

`tests/test_inject.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 18
```
[Credential-related source omitted]
```

`tests/test_install.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 30
```
[Credential-related source omitted]
```

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.

Signal confidence: 39 facts

Network access in prose of documentationREADME.md:5Low confidence
Network access in prose of documentationREADME.md:6Low confidence
Network access in code of documentationREADME.md:19Low confidence
Network access in code of documentationREADME.md:20Low confidence
Network access in prose of documentationREADME.md:113Low confidence
Network access in code of documentationREADME.md:126Low confidence
Network access in prose of documentationREADME.md:139Low confidence
Dangerous shell operation in prose of documentationREADME.md:213Low confidence
Network access in prose of documentationREADME.zh-CN.md:5Low confidence
Network access in prose of documentationREADME.zh-CN.md:6Low confidence
Network access in code of documentationREADME.zh-CN.md:18Low confidence
Network access in code of documentationREADME.zh-CN.md:19Low confidence
Network access in prose of documentationREADME.zh-CN.md:103Low confidence
Network access in code of documentationREADME.zh-CN.md:114Low confidence
Network access in prose of documentationREADME.zh-CN.md:126Low confidence
Dangerous shell operation in prose of documentationREADME.zh-CN.md:188Low confidence
Network access in prose of the SKILL.mdSKILL.md:24Low confidence
Network access in prose of the SKILL.mdSKILL.md:26Low confidence
Network access in prose of the SKILL.mdSKILL.md:71Low confidence
Network access in prose of the SKILL.mdSKILL.md:72Low confidence
Executable script in prose of a file that runshooks/_fable_common.py:1Low confidence
Executable script in code of a file that runshooks/fable_close_guard.py:1High confidence
Executable script in code of a file that runshooks/fable_fail_streak.py:1High confidence
Executable script in code of a file that runshooks/fable_lint.py:1High confidence
Executable script in code of a file that runshooks/fable_profile_inject.py:1High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehooks/fable_profile_inject.py:40Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehooks/fable_profile_inject.py:51Low confidence
Access to secrets in code of a file that runshooks/fable_profile_inject.py:165High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehooks/fable_profile_inject.py:166Low confidence
Executable script in code of a file that runshooks/fable_spawn_guard.py:1High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehooks/fable_spawn_guard.py:93Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehooks/fable_spawn_guard.py:112Low confidence
Executable script in code of a file that runsinstall.sh:1High confidence
Executable script in code of a testtests/test_guards.py:1Low confidence
Access to secrets in code of a test: a variable, placeholder or call, not a stored valuetests/test_guards.py:217Low confidence
Executable script in code of a testtests/test_inject.py:1Low confidence
Access to secrets in code of a test: a variable, placeholder or call, not a stored valuetests/test_inject.py:18Low confidence
Executable script in code of a testtests/test_install.py:1Low confidence
Access to secrets in code of a test: a variable, placeholder or call, not a stored valuetests/test_install.py:30Low 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.

cozytab/fable5-mode

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

fable-mode

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Before you install

README.md

README.zh-CN.md

SKILL.md

hooks/_fable_common.py

hooks/fable_close_guard.py

hooks/fable_fail_streak.py

hooks/fable_lint.py

hooks/fable_profile_inject.py

hooks/fable_spawn_guard.py

install.sh

tests/test_guards.py

tests/test_inject.py

tests/test_install.py

How the signals fit together

Works with

You might also use

OneWave-AI/claude-skills

gncdev/fabling

NousResearch/hermes-agent

aeonfun/aeon

affaan-m/ECC

xu-xiang/everything-claude-code-zh

`SKILL.md`

`README.md`

`README.zh-CN.md`

`SKILL.md`

`hooks/_fable_common.py`

`hooks/fable_close_guard.py`

`hooks/fable_fail_streak.py`

`hooks/fable_lint.py`

`hooks/fable_profile_inject.py`

`hooks/fable_spawn_guard.py`

`install.sh`

`tests/test_guards.py`

`tests/test_inject.py`

`tests/test_install.py`