fable-eval

fable-eval is a command for Claude Code from rennf93/opus-fable-playbook. It costs 38 tokens per session (264 once invoked), scanned A, original, MIT.

A command that runs fable-mode convergence tests: it compares two candidate modes with a baseline, checks them against expected results, and produces a report.

In plain words
What is it for?
Use it to run selected probes, create missing expected results, compare candidates, generate evaluation reports, and get recommendations for improvements.
Why use it?
It automates repeated evaluation runs and identifies the weakest quality area without changing the evaluated files.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the fable-mode plugin — 3 skills, 2 commands, 1 agent, 7 hooks shipped together

Good fit Use it to run selected probes, create missing expected results, compare candidates…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/rennf93/opus-fable-playbook/fable-eval
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.

Clone the repo
git clone --depth 1 https://github.com/rennf93/opus-fable-playbook

Made for: Claude Code.

Or install fable-mode, the plugin that ships this one along with the rest of its 3 skills, 2 commands, 1 agent, 7 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fable-eval

README.md
[![agentmods](https://agentmods.dev/badge/commands/rennf93/opus-fable-playbook/fable-eval.svg)](https://agentmods.dev/commands/rennf93/opus-fable-playbook/fable-eval)
Your own site
<a href="https://agentmods.dev/commands/rennf93/opus-fable-playbook/fable-eval"><img src="https://agentmods.dev/badge/commands/rennf93/opus-fable-playbook/fable-eval.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 264 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.00264
Opus 5 $0.00019 $0.00132
Sonnet 5 $0.00008 $0.00053
Haiku 4.5 $0.00004 $0.00026

Measured 7d ago against content hash eda8db6e79d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

fable-eval 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 7d 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.

commands/fable-eval.md · 19 lines

What it actually says

Run the fable-mode convergence evals. $ARGUMENTS may contain a probe id filter (e.g. 03), and --yes to skip the cost confirmation.

  1. Unless --yes was passed, tell the user how many probe runs this is (matched probes × 2 candidate modes + judging) and ask to proceed.
  2. Ensure goldens exist in evals/golden/ for the matched probes; for any missing, generate: evals/run-probe.sh <probe> golden evals/golden.
  3. Run baseline + fable candidates into evals/results/<today>/, then judge each against its golden, per evals/LOOP.md steps 1–2 (respect the filter).
  4. Run evals/report.sh evals/results/<today>/ and present the table.
  5. Interpret per LOOP.md step 4: name the weakest dimension and the exact doctrine section/hook/skill to strengthen. Do not apply changes — recommend them.
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. 7d ago First seen · 19 lines · 0 tokens per session scan A eda8db6e79d1

Subscribe to this mod's changes

fable-eval is a command published in the GitHub repository rennf93/opus-fable-playbook (34 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 264 once invoked, about $0.0002 per session on Opus 5. 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.