What's Inside

Agents1

fable-advisor

/fable-advisor

High-stakes decision advisor running on Claude Fable 5. Spawn for a single-shot strategic verdict on an architecture/design decision, a stuck debugging loop, a draft plan, a pre-completion review, or the design of an unattended loop/schedule/routine before it starts running — never for generation work. Expects a briefing packet (decision, options or loop design, constraints, evidence, file pointers); returns a terse committed verdict. Expensive model — consult per the fable-advisor skill's budget rules.

Skills1

fable-advisor

/fable-advisor

Decision protocol for consulting Claude Fable 5 (the top-tier, usage-billed model) as a strategic advisor from an Opus orchestrator session. Use BEFORE committing to any decision that would be costly to revert — system or workflow architecture, database schema and data-model design, API/webhook contracts, n8n workflow topology, technology and vendor selection, production migrations — even when you could decide yourself; deciding solo on a one-way door is exactly the failure mode this skill prevents. Fires on phrasings like "make the call", "decide between X and Y", "we'll live with this choice", "one-way door", "before we freeze it", "has to be right". Also use BEFORE starting any unattended loop, schedule, or routine — /loop, /schedule, /goal with a high turn cap, cron-style agents, proactive workflows — because a loop design flaw repeats every iteration; Fable reviews stop conditions, interval, verification, blast radius, and cost per iteration once, before it runs. Also use when stuck after 2+ genuinely different failed fix attempts, when finalizing an implementation plan (including in plan mode, before ExitPlanMode), before declaring done on hard-to-revert work (production deploys, migrations, client-facing deliverables), and whenever the user mentions Fable, a second opinion, an advisor, or checking with a stronger model. Covers when a consult is worth 2× Opus token prices, the compact briefing packet, per-task budget caps, and how to weigh the advice.

README

fables

Two Claude Code plugins for one problem: Claude Fable 5 is the best model and the most expensive one.

Each plugin is a small fable about using Fable 5 well, and both share a moral — judgment belongs on the strongest model, tokens belong on the cheapest one that can do the leg. Same economics, opposite directions:

Plugin	Direction	For sessions running on	One line
fable-advisor	consult up	Opus (or any model below Fable)	Buy Fable judgment rarely, at costly-to-revert inflection points, with a compact brief
fable-orchestrator	delegate down	Fable 5 (or any premium model)	Plan big, execute small: push bulk reading to cheap parallel workers, keep only distilled findings at Fable rates

Install one or both:

/plugin marketplace add czlonkowski/fables
/plugin install fable-advisor@fables
/plugin install fable-orchestrator@fables

fable-advisor (consult up)

Spend Fable 5 tokens only where they change the outcome.

Teaches an Opus orchestrator to consult Claude Fable 5 the way you'd use a top-dollar consultant: rarely, at the right moment, with a well-prepared brief, for a terse verdict. Day-to-day work runs on Opus. Fable gets called at inflection points: the decisions that are costly to revert once you start building.

Why

Fable 5 is billed at $10 / $50 per MTok — exactly 2× Opus 4.8 ($5 / $25). Left undisciplined, an orchestrator either never uses it (leaving quality on the table) or uses it lazily — full-context dumps, chatty back-and-forth, delegating generation — which burns money for nothing.

The protocol is adapted from Anthropic's advisor tool (executor + advisor pattern), rebuilt for local Claude Code orchestration where the advisor is a subagent and sees only what you send it — which is exactly where the token savings live.

A disciplined consult costs roughly $0.15–0.50. A wrong architecture costs hours of rework, thousands of Opus tokens, and your time.

What's inside

Component	What it does
Skill `fable-advisor`	The decision protocol: when to consult (and when not to), hard budget caps, the briefing-packet format, how to weigh the advice
Agent `fable-advisor`	A read-only subagent pinned to `model: fable` with a system prompt that enforces terse, committed verdicts (Verdict → Why → Risks → Would change my mind, ≤300 words)

Recommended: add this line to your project or global CLAUDE.md — it makes the skill fire deterministically instead of relying on Claude's own skill-triggering judgment (see Making it fire reliably for why):

Before committing to any costly-to-revert decision (architecture, DB schema, API/webhook
contracts, technology selection, production migration plans), before starting any
unattended loop/schedule/routine, or when stuck after 2+ failed fix attempts, consult
the fable-advisor skill first.

Requirements: Claude Code with Fable 5 available as a subagent model. Designed for sessions where the base model is Opus (works from any orchestrator model below Fable).

Making it fire reliably

We benchmarked the skill's triggering on 20 realistic queries (10 should-fire, 10 tricky near-miss negatives) across four description variants, ~200 runs on Opus. Result: zero false-fires in every variant — the skill never triggered on trivial changes, decided architectures, or questions about Fable — but recall on bare decision prompts plateaued around 50–60% regardless of description wording. The cause is structural: Claude Code consults skills only for tasks it can't handle alone, and Opus believes (correctly, in a narrow sense) that it can answer a design question itself. That belief is the exact failure mode this skill exists to counter.

If you want deterministic triggering, use the one-line CLAUDE.md setup above. Naming it also works: prompts that mention Fable, a "second opinion", or "check with a stronger model" trigger far more reliably (see Prompts to try below).