Tale Mode

Tale Mode

Anthropic pulled the plug on Fable. Tale Mode was made by Fable to get Opus to act like Fable.

Not smarter — more disciplined. A drop-in Claude Code plugin that makes any Claude work like a careful senior engineer: verify the real code (never memory), receipts on every decision, an independent adversarial review before it says "done," durable notes — and a self-armed autonomous loop that keeps going until a real check passes. Right-sized, so a typo fix stays a typo fix. The model got pulled; the method didn't.

Contents: Quick start · Problem · How it works · Examples · Use it · Autonomous loop · What's different · Install · Security & trust · Tuning · Does it work? · What's in the box · Managing / removing · Contributing

---

Quick start

/plugin marketplace add alicicek/tale-mode
/plugin install tale-mode@tale-mode

Restart Claude Code (so it loads), then just ask:

tale mode — refactor the auth middleware and prove it still blocks expired tokens

That's it. It picks how much process the task deserves, plans, verifies against the real code, and tells you what it couldn't check. For bigger work, reach for the /tale-mode:plan-phase → /tale-mode:kickoff-phase pipeline. Requires Claude Code ≥ v2.1.154.

The problem it targets

Strong models, under time pressure, predictably cut the same corners:

• act before understanding; one-shot a multi-step task
• trust their own summary of a file instead of re-reading it (stale claims, wrong line numbers, invented APIs)
• agree too readily and inscribe constraints nobody asked for
• review their own work — and miss the framing error they're inside
• drift on long tasks; forget earlier decisions
• declare "done" from the diff without running anything
• either over-engineer trivia or take shortcuts on the hard part

Tale Mode is a checklist-as-skill that targets each of these.

How it works

A right-size throttle decides how much process a task earns (and, for big work, how many phases to split it into) — so trivial work stays fast. Above that floor it runs an 8-step loop:

#	Step	What it forces
1	Map	Stage the work + define "done" before acting
2	Receipts	Every decision quotes a source or is labeled judgment
3	Delegate	Independent strands to parallel sub-agents (don't split coherent thought)
4	Verify twice	Internal consistency and against ground truth — a clean diff isn't evidence
5	Critique	Always self-critique; for high-stakes, a separate adversarial reviewer
6	Ask	Surface genuine forks instead of guessing
7	Persist	Progress to a durable file — the conversation isn't memory
8	Surface gaps	Name what's untested / out of scope

The three tiers the throttle picks from:

• 🟢 Trivial — a typo, a rename, a one-liner: just do it. No ceremony.
• 🟡 Substantial — multi-file but reversible, no auth/money/data: the light loop.
• 🔴 High-stakes — auth / money / data / security, or hard to undo: the full loop, including the independent reviewer and durable notes.

Examples

Same trigger, different amount of process — Tale Mode right-sizes to the task.

🟢 Trivial — it stays out of your way

tale mode — fix the typo in the pricing heading

Recognizes it's trivial and just does it: no staged plan, no sub-agents, no review. (Ceremony on a one-liner is its own failure mode.)

🟡 Substantial — the light loop (multi-file, reversible, no auth/money/data)

tale mode — migrate the marketing pages to the new framework

Maps the work, verifies its claims against the real files (re-reads them instead of trusting memory), self-critiques, and flags anything it couldn't check. Skips the heavyweight reviewer.

🔴 High-stakes — the full loop (auth / money / data / security, or hard to undo)

tale mode — implement Phase 2 of PLAN.md, only that phase

Re-verifies the plan against the actual code, interviews you on genuine forks, works on a dedicated branch, proves it by running it — and for cross-browser UI, checks a real WebKit/Safari render, not just Chromium — then runs an independent reviewer before you ship, and updates the plan file when done.

🔴 Where the independent reviewer earns its keep — money / security