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.
npx agentmods add skills/rellyholdem/fable-runner/fable-runnernpx skills add rellyholdem/fable-runner --skill fable-runnergit clone --depth 1 https://github.com/rellyholdem/fable-runnerWhat 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 | $0.00193 | $0.02401 |
| Opus 5 | $0.00097 | $0.01201 |
| Sonnet 5 | $0.00039 | $0.00480 |
| Haiku 4.5 | $0.00019 | $0.00240 |
Grade A, and why
fable-runner 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.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fable-runner — orchestrating the Fable 5 heavy model as a subagent
Fable 5 (claude-fable-5) is a very strong "heavy" model — it carries hard,
multi-step analysis/reverse-engineering/audit work better than the default. But
as a background subagent it is treacherous: it silently degrades to Opus, it
is slow enough to look hung, and it can flip models mid-run. This skill is the
vetted, empirically-proven playbook for getting real Fable work out of a
subagent and trusting the result.
Read this fully before spawning a model: fable subagent. For the wire-level
mechanism see references/mechanism.md; for ready-to-paste briefs/prompts see
references/templates.md; for a broader preflight lexicon see
references/trigger-lexicon.md.
Do not preload this skill into the Fable subagent. The parent/orchestrator
uses this skill to prepare the run. The Fable subagent should receive only the
neutral launch prompt and the sanitized brief. If you put fable-runner in the
subagent's skills field, Claude Code injects the full skill text into the
subagent context at startup, including the trigger vocabulary this file warns
about.
The core trap: "fable" silently becomes Opus
When you spawn a subagent with model: "fable", the harness can silently
serve Opus instead (claude-opus-4-8), and you will never be told. Two causes,
both proven empirically:
- A dumb keyword filter (the dominant cause). A safety classifier scans
everything Fable sees and, on a keyword hit (cybersecurity / exploit / DPI /
VPN / reverse-engineering / bypass / malware / attack / взлом / …), trips a
refusal-fallback to Opus and latches — once it flips, the rest of the
run stays Opus. It is keyword-based, not semantic: an A/B with two
identical benign tasks (write 5 nature haiku) gave 7/7 Fable for the clean
prompt and 4/4 Opus when the prompt's persona mentioned
"cybersecurity / exploits / DPI". The trigger fires from ANYTHING in context —
your launch prompt, the brief, files it reads, even the cwd path and injected
memory — not just your task text.
Official Fable 5 docs also identify safeguard areas for offensive cyber,
biology/life-sciences, and attempts to extract summarized thinking; benign
work in those areas can still trip the safeguard. Treat
references/trigger-lexicon.mdas a conservative preflight list, not as an exhaustive classifier spec. - Overload / parallel load. Under many concurrent Fable requests some get
served Opus. The
switchModelsOnFlagsetting only changes interactive behaviour (pause-and-ask); a background subagent has nobody to ask, so it falls through silently.
What ships with it
4 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.
- 2d ago First seen · 172 lines · 193 tokens per session scan A e05e75fbad0c
fable-runner is a skill published in the GitHub repository rellyholdem/fable-runner (3 stars, last pushed 2mo ago), licensed MIT. It adds 193 tokens to every session and 2,401 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
fablize
A harness that makes Opus (or any Claude model) behave like Fable — it enforces seeing a task through to the end, with evidence and verification, as procedure. Use when starting a multi-step task (2+ sequential stories), long autonomous work, debugging or root-cause investigation, building render/executable artifacts…
owner-facing-reporting
Use for every progress update, status report, problem explanation, ETA, review, acceptance, or completion report to the operator/owner, especially when they ask “到哪了”, “什么问题”, “做了什么”, “结果呢”, “还要多久”, or “说人话”. Translate technical evidence into visible or operational outcomes before details.
human-intent-audit
Enforce traceability from natural-language intent to machine predicates, final observables, evidence, and owner-readable acceptance. Use when conducting any audit, review, QA pass, parity or compliance check, security assessment, code or architecture review, visual or behavioral comparison, data validation, system…
visual-deck-studio
视觉演示工坊——用HTML做高保真原型、幻灯片、动画、可视化与专家评审，需求模糊时给设计方向。触发词：做原型、PPT、幻灯片、动画、设计风格、评审、做个HTML页面、UI mockup、导出MP4/GIF、做个好看的。生产级Web App/需后端的系统不适用。.
conducting-scientific-research
Conduct rigorous, reproducible multi-step scientific work with literature, databases, local files, Python, R, shell, artifacts, reviewers, and approved compute. Use for evidence synthesis, data or statistical analysis, machine learning, simulation, study design, scientific figures or manuscripts, reproduction audits…
verification-loop
Use when a task spans more than a few steps or files — establishes a checkable definition of done, a verification cadence, and fresh-context verifier subagents before claiming completion.