SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-17 UTC

No new commits yet today

Open the update feed

fable-modemrtooher/fable-mode

Provides a workflow constraint layer for AI agents that schedules by model capability tier, plans before acting,…

No ratings yet Rate this skill
Stars873
Forks95
Watchers873
Open Issues0

InstallOne-line install

Installable · 12 skills

This repository follows the Agent Skills spec, so one command installs it into your AI client — works across Claude Code, Codex, Cursor, Copilot, Windsurf, and 18+ other clients.

npx skills@latest add mrtooher/fable-mode

This repository bundles 12 skills, and you can install just one:

9 more are not listed — run npx skills@latest add mrtooher/fable-mode --list to see them all.

Add -g install globally (available in every project) · add --agent claude-code to target a client · add --yes to skip the prompts. Restart your AI client afterward and it will pick it up.

OverviewOverview

Key Features

Provides a workflow constraint layer for AI agents that schedules by model capability tier, plans before acting, and double-checks before and after execution, preventing agents from skipping steps, writing code arbitrarily, or delivering unverified conclusions. Key capabilities include: 1. Tiered model scheduling: assigns tasks across Frontier/Sonnet/Haiku tiers, giving complex planning to high-capability models and simple execution to lightweight models to cut wasted calls and cost; 2. Stage map first: forces generation of a stage map before acting, breaking the task into checkable steps to prevent jumping straight into coding; 3. Delegate by precisely delegates subtasks to the matching skill or sub-agent by name, avoiding role confusion and duplicated work; 4. Execution guardrails: forces matching and activation of the corresponding skill at session initialization, blocking agents from writing code or acting beyond authority without authorization; 5. Self-critique and double-check: performs self-critique before output and then a double-check, intercepting logic gaps and factual errors before delivery.

Use Cases

decomposition and orchestration of multi-step complex tasks, tiered model scheduling to control cost, pre-execution self-check and post-execution double verification, precise delegation of subtasks by name, self-critique and correction before output, preventing agents from acting without authorization.

Target Roles

AI / Algorithm Engineer, Backend Developer, Full-stack / Indie Developer, Product Manager (PM).

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID1098
Data sourceGitHub
Repositorymrtooher/fable-mode
CategoryAI & Agent Development / Agent Workflow & Orchestration
Primary languagePython
LicenseNot specified
Default branchmain
GitHub repository ID1268068714
Node IDR_kgDOS5Uxag
Rank#846 (position within the source ranking)
Site-wide popularity rank#957 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02505007501k2026-09-292026-10-112026-09-29 · 8692026-10-11 · 873
  • Now873
  • Previous point · 09-29 869
  • vs previous point +4
  • 2 data points 12 days
02550751002026-09-292026-10-112026-09-29 · 942026-10-11 · 95
  • Now95
  • Previous point · 09-29 94
  • vs previous point +1
  • 2 data points 12 days

TimelineTimeline

Repository created2026-06-13 05:33:145 months ago
Data last updated2026-10-26 12:04:5721 days ago
Last commit2026-10-11 05:09:171 months ago

CommitLatest commit

Committed by 匿名贡献者. Update Category: Routine Updates & Maintenance. Commit details: Remove whistlepot-gateway (personal contact info). This update performs routine maintenance and minor adjustments.

c6d6e7f 2026-10-11