fable-5-usage

fable-5-usage is a skill for Claude Code, Codex from DanceNitra/agora. It costs 0 tokens per session (1,678 once invoked), scanned A, original, MIT.

A guide for choosing when to use Claude Fable 5, an AI model, instead of other Claude models, and for configuring prompts for it. It is based on a dated research briefing with checked citations and stated limitations.

In plain words
What is it for?
Deciding which Claude model should handle a task and writing or configuring prompts for Claude Fable 5.
Why use it?
It helps developers choose among models and avoid treating vendor-reported test results as independent proof of quality.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/dancenitra/agora/fable-5-usage
Any agent
npx skills add DanceNitra/agora --skill fable-5-usage
Clone the repo
git clone --depth 1 https://github.com/DanceNitra/agora

Made for: Claude Code, Codex.

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-5-usage

README.md
[![agentmods](https://agentmods.dev/badge/skills/dancenitra/agora/fable-5-usage.svg)](https://agentmods.dev/skills/dancenitra/agora/fable-5-usage)
Your own site
<a href="https://agentmods.dev/skills/dancenitra/agora/fable-5-usage"><img src="https://agentmods.dev/badge/skills/dancenitra/agora/fable-5-usage.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,678 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01678
Opus 5 $0.00000 $0.00839
Sonnet 5 $0.00000 $0.00336
Haiku 4.5 $0.00000 $0.00168

Measured 5d ago against content hash c7a9d8a5819d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fable-5-usage 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 5d 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/skills/fable-5-usage/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fable 5 usage — when to route to Claude Fable 5, and how to prompt it

What this is

Operational guidance for deciding when to route work to claude-fable-5 (vs Opus 4.8 / Sonnet 5 / Haiku 4.5) and how to prompt/configure it for best results. Distilled from a 5-lens Storm Research run (Practitioner, Academic, Skeptic, Economist, Historian) whose lens agents ran ON Fable 5 itself, on 2026-07-03. Full briefing: storm-reports/claude-fable-5-best-uses-prompting-briefing.html.

VERIFIED 2026-07-03 (16/16 citations checked vs primary sources; 2 lens fabrications removed, 4 corrected). Pricing, thinking-always-on, effort knob, server-side fallback, 30-day retention, and the export-control pull/redeploy are CONFIRMED against Anthropic docs. Caveats that remain: the headline coding gaps (SWE-bench Pro 80.3 vs 69.2) are Anthropic-run, the one independent real-scenario eval (Tessl, 917 tasks) shows only +0.9 pts / 61% ties, the Artificial Analysis #1/score-60 is vendor-adjacent and config-specific, and the public record is days old across two safety stacks. So: the operational rules are the load-bearing takeaway; the numbers are now verified but mostly vendor-sourced — keep A/B-ing on your own workload. Full briefing has per-citation tags.

The one-line policy

Do not make Fable 5 the default. Keep Opus 4.8 (or Sonnet 5 for volume) as the daily driver; buy up to Fable 5 per-task, with evidence, for the hard tail. Never default down from it. (Its edge is real but concentrated in the hardest few percent of tasks; on everyday work it roughly ties Opus 4.8 at 2× sticker / ~3–5× effective cost.)

Routing — where Fable 5 earns its price

Route TO Fable 5:

  • A problem Opus/Sonnet failed on repeatedly (stuck bug, gnarly multi-step refactor). Operators report it one-shotting clusters Opus 4.8 failed ~16× on.
  • Long-horizon autonomous / overnight runs; whole-repo reasoning that genuinely needs the 1M-token window.
  • Multi-agent orchestration; hard ambiguous synthesis.

Read the full file on GitHub · 93 lines

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. 5d ago First seen · 93 lines · 0 tokens per session scan A c7a9d8a5819d

Subscribe to this mod's changes

fable-5-usage is a skill published in the GitHub repository DanceNitra/agora (3 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,678 tokens. 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 2026-08-31.

Related

Other skills, from other repositories

Evaluation

Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.

agentic-in/elephant-agent · 25 tokens

create-custom-grader

Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.

NVIDIA/SkillEvaluator · 35 tokens

ceo-setup

One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.

suyoumo/ClawProBench · 60 tokens

developer-setup

One-time onboarding for the developer workflow — installs github-workflow missions, creates the commitments workspace, registers per-repo projects, writes calibration memories. After successful setup this skill is excluded from selection until the marker file is deleted.

suyoumo/ClawProBench · 49 tokens

commitment-setup

One-time setup for the commitments tracking system. Creates workspace structure, schema docs, and installs triage and digest missions. Excluded from activation once projects/commitments/README.md exists in the workspace (the file this skill writes as its first step).

suyoumo/ClawProBench · 58 tokens

content-creator-setup

One-time onboarding for the content creator workflow — content pipeline stages, trend expiration, cross-platform cascades, heavy idea parking. After successful setup this skill is excluded from selection until the marker file is deleted.

suyoumo/ClawProBench · 47 tokens