fables

A marketplace package containing two tools: one for consulting Claude Fable 5 and one for coordinating cheaper helpers from a Fable session.

In plain words
What is it for?
Use it for strategic architecture or debugging advice, and for parallel codebase, log, document, web, or coverage investigations.
Why use it?
It provides both directions of delegation: getting higher-level advice for important decisions and moving routine reading away from an expensive model.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add czlonkowski/fables
agentmods
npx agentmods add plugins/czlonkowski/fables/marketplace
Clone the repo
git clone --depth 1 https://github.com/czlonkowski/fables

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

fables scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/marketplace.json · 25 lines

What it actually says

{
  "name": "fables",
  "owner": {
    "name": "Romuald Członkowski",
    "email": "[email protected]",
    "url": "https://aiadvisors.pl/en"
  },
  "metadata": {
    "description": "Two protocols for Fable 5 economics in Claude Code: consult up (fable-advisor — an Opus orchestrator buys Fable judgment at inflection points) and delegate down (fable-orchestrator — a Fable session pushes bulk reading to cheap parallel workers).",
    "version": "0.4.0"
  },
  "plugins": [
    {
      "name": "fable-advisor",
      "source": "./plugins/fable-advisor",
      "description": "Consult Claude Fable 5 as a strategic advisor at costly-to-revert inflection points: architecture decisions, stuck debugging, plan review, pre-completion review, and unattended loop/schedule design. Compact briefing packets, hard budget caps, terse verdicts — judgment from Fable, tokens from Opus."
    },
    {
      "name": "fable-orchestrator",
      "source": "./plugins/fable-orchestrator",
      "description": "Run Fable 5 as a coordinator: plan big, execute small. Bulk reading — codebase sweeps, log triage, document review, web research, coverage verification — fans out to parallel workers pinned to Sonnet/Haiku, and only distilled findings enter Fable's premium context. Ported to Claude Code from Anthropic's plan-big-execute-small cookbook."
    }
  ]
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 25 lines scan A 2efc56f5da92

Subscribe to this mod's changes

fables is a plugin published in the GitHub repository czlonkowski/fables (20 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.