#983 by GitHub stars
mrtooher/fable-mode
A Claude skill that activates Fable-style agentic behavior: explicit multi-stage planning, sub-agent delegation, and self-verification.
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
c2d8e6c64abb → c2d8e6c64abb
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → c2d8e6c64abb
No earlier version was observed for comparison.
double-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
c2d8e6c64abb → c2d8e6c64abb
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → c2d8e6c64abb
No earlier version was observed for comparison.
execution-guardrails/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
c2d8e6c64abb → c2d8e6c64abb
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → c2d8e6c64abb
No earlier version was observed for comparison.
fable-fable/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
c2d8e6c64abb → c2d8e6c64abb
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → c2d8e6c64abb
No earlier version was observed for comparison.
fable-haiku/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
c2d8e6c64abb → c2d8e6c64abb
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → c2d8e6c64abb
No earlier version was observed for comparison.
fable-opus/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
c2d8e6c64abb → c2d8e6c64abb
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → c2d8e6c64abb
No earlier version was observed for comparison.
fable-sonnet/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
c2d8e6c64abb → c2d8e6c64abb
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → c2d8e6c64abb
No earlier version was observed for comparison.
Heat
3.9- Star growth, last 7 daysAhead of 74% of tracked repositories
- Star growth, last 24 hoursAhead of 2% of tracked repositories
- Rank movement, last 7 daysAhead of 4% of tracked repositories
- Commits, last 30 daysAhead of 80% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- fable-mode
/ - double-check
double-check - execution-guardrails
execution-guardrails - fable-fable
fable-fable - fable-haiku
fable-haiku - fable-opus
fable-opus - fable-sonnet
fable-sonnet
How it works
fable-mode
When your agent uses it
Enforces staged execution discipline on large tasks: a written stage plan, parallel delegation where the runtime supports it, a failable verification check at each stage, and a skeptical self-review before delivery. Trigger when the user explicitly asks OR when the task objectively spans multiple files, sources, or sessions. Do NOT trigger on ordinary multi-step requests that a direct attempt handles fine (autonomous triggering only; explicit invocation always runs).
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
3,926 tokensWhen the skill is activated
Reference documents
16,179 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Invocation gate
- When NOT to use this (autonomous trigger only)
- Calibrate to the model running it
- Core Loop
- Domain-specific patterns
- Operational rules
- What this skill doesn't do
Scripts executed separately
bench/checker/audit_key.pybench/checker/gen.pybench/checker/score.pybench/grade.pybench/make_fixtures.pyinstall.shscripts/validate_skills.pytests/test_validate_skills.py
Files
.gitignoreasset42 bytesBENCHMARK-2026-09-02.mddoc5,412 bytesEXAMPLE.mddoc8,944 bytesREADME.mddoc7,402 bytesSKILL.mdcore17,387 bytesSKILL.mdcore17,387 bytesSKILL.mdcore17,387 bytesSUPERSEDED.mddoc1,932 bytesV3-CHANGES.mddoc3,076 bytesagents/fable-orchestrator.mddoc6,102 bytesagents/fable-verifier.mddoc1,930 bytesagents/fable-worker-haiku.mddoc2,597 bytesagents/fable-worker-sonnet.mddoc2,726 bytesbench/README.mddoc880 bytesbench/checker/README.mddoc1,213 bytesbench/checker/RESULTS.mddoc1,587 bytesbench/checker/audit_key.pyruns7,421 bytesbench/checker/gen.pyruns17,684 bytesbench/checker/score.pyruns2,540 bytesbench/grade.pyruns8,922 bytesbench/judgment/README.mddoc2,327 bytesbench/judgment/results.xlsxasset13,810 bytesbench/judgment/rules/rules-A.mddoc1,208 bytesbench/judgment/rules/rules-B.mddoc2,859 bytesbench/judgment/test1/key.mddoc1,085 bytesbench/judgment/test1/memo.mddoc1,294 bytesbench/judgment/test1/spec.mddoc1,241 bytesbench/judgment/test2/key.mddoc1,412 bytesbench/judgment/test2/memo.mddoc2,670 bytesbench/judgment/test2/spec.mddoc1,640 bytesbench/make_fixtures.pyruns10,507 bytesbench/prompt_base.txtdoc267 bytesbench/prompt_skill.txtdoc6,805 bytesbench/results.jsonasset5,388 bytesbench/skill_briefing.mddoc6,255 bytesbench/truthA.jsonasset1,094 bytesbench/truthC.jsonasset488 bytesbench/truthD.jsonasset912 bytesinstall.shruns817 bytesscripts/validate_skills.pyruns6,719 bytestests/test_validate_skills.pyruns9,317 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdouble-check
When your agent uses it
Automatic final verification pass on completed deliverables. Runs at the end of every fable-mode run — those skills invoke it before delivery. Also triggers when the user says "double check this". Uses a panel of fresh checker agents when spawning is authorized (otherwise a cold self-check) to verify the finished output — not to redo the task. Any FAIL gets fixed and re-checked before delivery.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
2,807 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What it is and is not
- When it runs
- Skip conditions
- The core rule: pass the claims, never the reasoning
- Procedure
- Operational rules
Files
SKILL.mdcore11,861 bytesSKILL.mdcore11,861 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubexecution-guardrails
When your agent uses it
Always-on operational guardrails, model-independent. Apply on EVERY task and EVERY model whether or not fable-mode's staged loop is running. Three rules: verify-before-flag, warning batching, and find-and-replace safety. Trigger whenever a response would flag a problem, raise a warning, or edit files with search-and-replace.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
816 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Verify before flag
- 2. Warning threshold
- 3. Find-and-replace safety
- Relationship to fable-mode
Files
SKILL.mdcore3,694 bytesSKILL.mdcore3,694 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubfable-fable
When your agent uses it
Run fable-mode execution discipline on Claude Fable 5.1 — the top of the escalation ladder and the strongest staged run available. Routes the task to the @fable-orchestrator agent with its model overridden to Fable (`model: "fable"`), which stages the work, delegates artifact production to @fable-worker-sonnet / @fable-worker-haiku, and cold-checks deliverables with @fable-verifier. Trigger when the user explicitly asks for thorough/systematic/"deep work" handling on the strongest model ("fable on fable", "stage this on fable", "deep work mode, fable", "run this on 5.1"), or when a fable-opus run reports the task exceeds Opus's ceiling. Benchmarked 2026-09-02: zero correctness delta on Fable 5.1 at ~1.1× tokens, ~2× wall — a provenance runner, not an accuracy runner. Do NOT use for ordinary single-pass tasks — prefer fable-opus, fable-sonnet, or fable-haiku when the task doesn't need peak reasoning. Fable is plan-included; bulk work still routes down-tier.
What it loads into context
Frontmatter
282 tokensAlways available to the agent
SKILL.md
1,114 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How to run it
- Known limitation
Files
SKILL.mdcore4,355 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubfable-haiku
When your agent uses it
Run fable-mode execution discipline on Claude Haiku. Routes the task to the @fable-worker-haiku agent, whose definition carries the staged loop with tightened verification (no bare "unverified" allowed) and an escalate-don't-improvise rule. Trigger when the user explicitly asks for thorough/systematic handling run cheaply or fast ("fable on haiku", "deep work mode but cheap", "stage this on haiku"). For bulk mechanical work. Do NOT use for tasks needing synthesis — benchmark note: at n=1 the skill's effect on Haiku swung both directions (+25 / −17); route quality-critical work to fable-sonnet instead.
What it loads into context
Frontmatter
163 tokensAlways available to the agent
SKILL.md
554 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How to run it
Files
SKILL.mdcore2,269 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubfable-opus
When your agent uses it
Run fable-mode execution discipline on Claude Opus — the top of the escalation ladder. Trigger when the user explicitly asks for thorough/systematic/"deep work" handling on Opus ("fable on opus", "stage this on opus", "deep work mode, opus"). When a task exceeds Opus's ceiling, report that to the user rather than escalating further.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
2,030 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Invocation gate
- How to run it
- Execution guardrails (inline these into every worker briefing)
- Known limitation
Files
SKILL.mdcore8,525 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubfable-sonnet
When your agent uses it
Run fable-mode execution discipline on Claude Sonnet. When invoked by slash command or by name, spawns a Sonnet subagent that follows the staged loop — stage plan, parallel delegation, a failable verification check at each stage, and a skeptical self-review before delivery; a wording-only request runs the loop inline on the current model. Trigger when the user explicitly asks for thorough/systematic/"deep work" handling on Sonnet.
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
2,242 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Invocation gate
- How to run it
- Core Loop (pass this to the subagent)
- Domain patterns (pass these to the subagent too)
- Operational rules (pass these to the subagent verbatim)
Files
SKILL.mdcore10,090 bytesSKILL.mdcore10,090 bytesSKILL.mdcore10,090 bytesSKILL.mdcore10,090 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- fable-mode
- double-check
- execution-guardrails
- fable-fable
- fable-haiku
- fable-opus
- fable-sonnet
Repository facts
- License
- No license detected
- Created
- Jun 13, 2026
- Last pushed
- Oct 24, 2026
- Forks
- 95
- Open issues
- 0
- Project activity
- Active
Rank over the last 12 weeks
Now #983 · best #630 · down 248 in 30 days
- #967 on Nov 1
- #973 on Nov 2
- #976 on Nov 3
- #982 on Nov 4
- #979 on Nov 5
- #983 since Nov 6
51 earlier periods
- #709 on Aug 1
- #620 on Aug 7
- #617 on Aug 8
- #622 on Aug 9
- #654 on Aug 12
- #647 on Aug 14
- #651 on Aug 17
- #668 on Aug 18
- #652 on Aug 19
- #655 on Aug 20
- #630 on Aug 22
- #661 on Aug 23
- #681 on Aug 24
- #684 on Aug 25
- #665 on Aug 26
- #677 on Aug 27
- #699 on Aug 28
- #648 on Aug 29
- #647 on Aug 30
- #680 on Aug 31
- #691 on Sep 1
- #683 on Sep 2
- #688 on Sep 3
- #666 on Sep 4
- #656 on Sep 5
- #678 on Sep 6
- #703 on Sep 9
- #710 on Sep 10
- #693 on Sep 11
- #720 on Sep 14
- #711 on Sep 15
- #724 on Sep 17
- #706 on Sep 18
- #681 on Sep 19
- #718 on Sep 21
- #739 on Sep 22
- #719 on Sep 27
- #766 on Sep 29
- #744 on Sep 30
- #735 on Oct 5
- #798 on Oct 8
- #765 on Oct 9
- #755 on Oct 11
- #793 on Oct 14
- #769 on Oct 17
- #823 on Oct 21
- #938 on Oct 25
- #956 on Oct 28
- #959 on Oct 29
- #961 on Oct 30
- #965 on Oct 31
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 7 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddouble-check/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexecution-guardrails/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedfable-sonnet/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedfable-sonnet/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedfable-sonnet/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 16 network referencesin 4 files: bench/results.json:207 bench/judgment/README.md:6 README.md:96 and 1 more
- No hidden or obfuscated text
- No instruction overrides
- 8 executable scriptsin 8 files: bench/checker/audit_key.py:1 bench/checker/gen.py:1 bench/checker/score.py:1 and 5 more
- 1 reference to secretsin 1 file: bench/grade.py:74
- No requests to vote in Hot
Show all 25 signals by file
README.md
- Network accessline 96
git clone https://github.com/mrtooher/fable-mode.git && cd fable-mode && ./install.sh
bench/checker/audit_key.py
- Executable scriptline 1
Executable file
bench/checker/gen.py
- Executable scriptline 1
Executable file
bench/checker/score.py
- Executable scriptline 1
Executable file
bench/grade.py
bench/judgment/README.md
bench/make_fixtures.py
- Executable scriptline 1
Executable file
bench/results.json
- Network accessline 207
"score": 100, "detail": { "source": "https://www.niaaa.nih.gov/sites/default/files/pcyr1970-2023.txt", - Network accessline 208
"detail": { "source": "https://www.niaaa.nih.gov/sites/default/files/pcyr1970-2023.txt", "source_is_niaaa": true, - Network accessline 209
"source": "https://www.niaaa.nih.gov/sites/default/files/pcyr1970-2023.txt", - Network accessline 219
"score": 100, "detail": { "source": "https://www.niaaa.nih.gov/sites/default/files/pcyr1970-2023.txt", - Network accessline 220
"detail": { "source": "https://www.niaaa.nih.gov/sites/default/files/pcyr1970-2023.txt", "source_is_niaaa": true, - Network accessline 221
"source": "https://www.niaaa.nih.gov/sites/default/files/pcyr1970-2023.txt", - Network accessline 231
"score": 100, "detail": { "source": "https://www.niaaa.nih.gov/sites/default/files/pcyr1970-2023.txt", - Network accessline 232
"detail": { "source": "https://www.niaaa.nih.gov/sites/default/files/pcyr1970-2023.txt", "source_is_niaaa": true, - Network accessline 233
"source": "https://www.niaaa.nih.gov/sites/default/files/pcyr1970-2023.txt", - Network accessline 243
"score": 100, "detail": { "source": "https://www.niaaa.nih.gov/sites/default/files/pcyr1970-2023.txt", - Network accessline 244
"detail": { "source": "https://www.niaaa.nih.gov/sites/default/files/pcyr1970-2023.txt", "source_is_niaaa": true, - Network accessline 245
"source": "https://www.niaaa.nih.gov/sites/default/files/pcyr1970-2023.txt",
install.sh
- Executable scriptline 1
#!/usr/bin/env bash
scripts/validate_skills.py
tests/test_validate_skills.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.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| 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.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/mrtooher-fable-mode/)