Borrowing it
Nothing to install: this file belongs to Dynokostya/just-works. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Dynokostya/just-works/main/.claude/skills/fable-5-1-prompting/SKILL.mdgit clone --depth 1 https://github.com/Dynokostya/just-worksWrote 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.
[](https://agentmods.dev/skills/dynokostya/just-works/fable-5-1-prompting)<a href="https://agentmods.dev/skills/dynokostya/just-works/fable-5-1-prompting"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/fable-5-1-prompting/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dynokostya/just-works/fable-5-1-prompting"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/fable-5-1-prompting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00074 | $0.03798 |
| Opus 5.5 | $0.00030 | $0.01519 |
| Sonnet 5.5 | $0.00015 | $0.00760 |
| Haiku 4.5 | $0.00007 | $0.00380 |
Grade A, and why
fable-5-1-prompting 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fable 5.1 Prompting
When to Use
- Creating or editing system prompts targeting Claude Fable 5.1
- Designing long-running autonomous agents, harnesses, or subagent orchestration on Fable 5.1
- Migrating prompt text from Fable 5, Opus 5, Opus 4.8, or older Claude models
- Diagnosing early stopping, missing progress updates, one-tool-per-turn loops, out-of-scope edits, or refusals on Fable 5.1
Overview
Claude Fable 5.1 is Anthropic's model for demanding reasoning and long-horizon agentic work. For most other workloads start with Opus 5.5 (see opus-5-5-prompting). Anthropic reports it is particularly effective at end-to-end work that takes a person hours, days, or weeks, and that testing it only on simple workloads undersells it (https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5).
Prompts written for Fable 5 should perform well on Fable 5.1 unchanged; the changes below are tuning (https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1). Thinking is always on, so prompt text that assumes a no-thinking mode is obsolete.
- Strong instruction following. A brief instruction steers most behaviors, and explicit tool instructions are followed reliably (Fable 5 page).
- Fewer progress updates. Fewer user-facing updates than Fable 5, more so at higher effort and in long tool chains. The notes arrive as progress-update thinking blocks, which are empty under the default
thinking.displayof"omitted". - One tool call per turn. In coding and computer-use loops where independent calls are implied rather than requested, it may issue them one per turn.
- Denser prose, lighter formatting. Sentences run longer with fewer paragraph breaks; in chat it uses less bold, fewer headers and lists.
- Unmarked quotation. It reproduces passages of source text without marking them as quotes.
- Unrequested extras. It sometimes fixes nearby code, extends behavior, or commits more tests than the task needs. It can also take unrequested actions such as drafting an email or making defensive git-branch backups (Fable 5 page).
- Rare early stopping. Deep into long sessions it can end on a statement of intent without the tool call, or pause for permission it does not need (Fable 5 page).
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago Changed · -9 tokens per session b6038bac5f2a
- 17d ago Changed · -159 lines scan B → A c573ec3fc3b9
- 1mo ago First seen · 341 lines · 83 tokens per session scan B 32171f426151
fable-5-1-prompting is a skill published in the GitHub repository Dynokostya/just-works (14 stars, last pushed 10d ago), licensed Apache-2.0. It adds 74 tokens to every session and 3,798 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-24.
fable-5-1-prompting compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fable-5-1-promptingDynokostya/just-works | Skill | 14 | 10d ago | Apache-2.0 | A | 74 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |