MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It introduces a sophisticated model-aware architecture for AI-assisted coding sessions, enabling seamless coordination between different models with automatic redirection and escalation patterns.
Who it is for
- Developers using Claude Code with multiple model tiers
- Teams building custom AI coding workflows
- Users who frequently switch models mid-session
- Developers interested in agent orchestration patterns
Use cases
- Automatically routing complex decision-making to stronger models (Opus) while delegating volume work to Sonnet
- Using Fable as a frontier coordinator to plan and delegate tasks to Codex and Sonnet workers
- Ensuring correct skill activation even after mid-session model switches
- Building a scalable multi-agent coding assistant that adapts to the available model strength
Strengths
- Model detection script accurately determines live model despite mid-session switches and stale transcript data
- Co-installable design with automatic redirection to the correct sibling skill
- Clear separation of concerns: advisor for escalation pattern, coordinator for frontier delegation
- Lightweight filesystem skills with no external dependencies
Considerations
- Only applies when the main model is Opus or Fable; no effect on Sonnet- or Haiku-led sessions
- Requires both skill folders to be co-installed in the skills directory
README quick start
fable-advisor + fable-coordinator
A matched pair of Claude Code skills encoding one subject — Fable 5's role in a session — split by the session's main model so each session loads only the half that applies.
| Skill | Applies when main model is | Role |
|---|---|---|
fable-advisor | Opus | Opus orchestrates, Sonnet does the volume workers, and a Fable subagent advises at genuine decision points (the escalation pattern — consult a stronger model on the hard calls). |
fable-coordinator | Fable | Fable is the frontier coordinator — plan big, execute small: keep only non-transferable in-session judgment, route self-contained frontier-grade legs to a Codex delegate, and fan mechanical legs out to Sonnet workers. |
On a Sonnet- or Haiku-main session, neither applies.
Step-0 model probe
Both skills must know the session's current main model — and a model can't reliably
report its own identity after a mid-session /model switch, because the conversation
history keeps it anchored to what it was earlier. So each skill opens with a deterministic
step 0 that derives the live model from the session transcript rather than trusting
self-image, via the shared script
fable-advisor/scripts/current-model.sh. It
prints one token — opus, fable, sonnet, haiku, or unknown — and each skill
branches on it, redirecting to its sibling if the wrong half loaded. The script is careful
about transcript flush timing (a naive read of the last assistant message's model is stale
exactly at step 0) and is hardened against tool-output that merely quotes model ids; the
full rationale is in fable-advisor/README.md.
Install
Both are filesystem skills — drop the two folders into your skills directory (e.g.
~/.claude/skills/) so Claude Code discovers them at session start. The pair is designed
to be co-installed: fable-coordinator calls the probe script that lives under
fable-advisor/. See each folder's README.md for details and the automatic-firing setup.
Description
Claude skill: consult a stronger Fable 5 advisor subagent at decision points (Opus orchestrates, Sonnet workers, Fable advises).
Related repositories
Similar projects matched by category, topics, and programming language.
xuchonglang
Featured
investing-for-beginners
A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.
Krishnagangwal
Featured
CS-Fundamentals
A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.