Fable Mode

Agents that think before they write.

       

Fable Mode is an open-source control plane for AI coding agents.

It makes an agent deliberate, produce evidence, and survive adversarial review before it earns permission to write to your workspace. The gates are mechanical, not prompt advice: no timer, no proof, no write access.

Demo

KERR // ORRERY

One self-contained HTML file. Raw WebGL, zero libraries, zero external assets, and zero build step.

https://github.com/user-attachments/assets/8287bbfe-e3ee-4dcf-ba0f-f9ff22ae79bd

_{7 renders rejected before final · 2 bugs caught · 10/10 red-team probes passed}

Fable Mode overview

https://github.com/user-attachments/assets/27f4f8a2-b1bb-4398-a08c-bc9fd93d69d7

Quick start

A session starts locked. Confidence does not unlock it.

1. Install the MCP server using one of the options below.
2. Add the optional Agent Skill if you want the full workflow.
3. Ask your agent to use Fable Mode for a concrete coding task and choose a time budget.

A new session starts with execution locked:

{
  "action": "create_session",
  "session_name": "demo-refactor",
  "objective": "Refactor the parser without changing public behavior",
  "time_budget_minutes": 2
}

The agent then records evidence and an invariant. An early unlock_execution request is rejected until the authority timer and proof prerequisites pass. Use get_status at any point to see the active phase, remaining time, evidence counts, and lock state.

The same gates guard every phase: evidence receipts for claims, a five-vector red-team swarm for code, and a sealed record of what was verified.

Install

pip install fable-engine

Or install the MCP server in your editor:

These links configure Fable Engine for AI agents in VS Code Chat or Cursor. They do not install a standalone editor extension. Both use uvx, which downloads and runs the pinned PyPI release in an isolated environment.

Point your agent at the MCP server manually:

// Claude Code: claude mcp add fable-engine -- uvx --from fable-engine==1.3.6 fable-engine
// Cursor: ~/.cursor/mcp.json
{
  "mcpServers": {
    "fable-engine": {
      "command": "uvx",
      "args": ["--from", "fable-engine==1.3.6", "fable-engine"]
    }
  }
}

Python 3.10+, zero runtime dependencies. Published on PyPI as fable-engine.

Optional: the Agent Skill

Installing fable-engine gives your agent the MCP tools. It does not install or activate the Fable Mode Agent Skill - the prompt-side workflow in skills/fable-mode. Nothing in the package activates those instructions on its own; the skill is always a separate, explicit opt-in.

The complete skill tree ships inside the wheel. To install it into your project's skills directory (the cross-client .agents/skills/ convention):

uvx --from fable-engine==1.3.6 fable-mode install-skill --yes

This copies the skill to .agents/skills/fable-mode. Preview first with --dry-run, choose another location with --target <dir>, and reload your agent afterwards so it picks up the skill.

How it works

1. Think — Time-locked deliberation. The agent cannot write until the timer ends.
2. Prove — Claims need real evidence (tool receipts, hashes, invariants).
3. Attack — A red-team swarm tries to break the code.
4. Write — Only then is the workspace unlocked.

Optional: AI evidence adjudicator

The evidence in a session is written by an AI agent, so Fable can optionally ask an external reviewer model to audit that evidence before the workspace unlocks. Stdlib-only, one bounded HTTPS call, no local model, no extra RAM to speak of. Off by default; fail-closed when enforcing. It raises the cost of fabricated proof - it cannot guarantee deception is impossible, and the mechanical gates stay the primary authority. Setup and honest limits: AI evidence adjudicator.

What it is not

• Not a claim of flawless code. It is a checkable workflow, not a guarantee.
• Not a bigger prompt. The locks are enforced by the engine, not by wording.
• Not a framework lock-in. It speaks MCP and runs beside your current agent.

Docs

• Start here: practical guide
• Agent Skill reference
• V1 → V2 migration
• V2 architecture
• System 3 (experimental)
• AI evidence adjudicator (optional)

Contributing

Issues and pull requests are welcome. See CONTRIBUTING.md.