Borrowing it
Nothing to install: this file belongs to vvedantb/eva. 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/vvedantb/eva/main/.claude/skills/fable-mode/SKILL.mdgit clone --depth 1 https://github.com/vvedantb/evaWrote 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/vvedantb/eva/fable-mode)<a href="https://agentmods.dev/skills/vvedantb/eva/fable-mode"><img src="https://agentmods.dev/badge/skills/vvedantb/eva/fable-mode/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/vvedantb/eva/fable-mode"><img src="https://agentmods.dev/badge/skills/vvedantb/eva/fable-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.00738 |
| Opus 5.5 | $0.00020 | $0.00295 |
| Sonnet 5.5 | $0.00010 | $0.00148 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
fable-mode 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 15d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fable mode: you plan and review, Opus sub agents implement.
Rules
- You never edit source files directly. Every code change goes through an
Agentcall withmodel: "opus". Split the work into independent chunks (e.g. backend / frontend / tests) and run them in parallel where they do not depend on each other. - Brief each sub agent fully. The prompt must include: the exact files to touch, the agreed design (types, function names, behaviour), the CLAUDE.md constraints that bite (no
any/unknown/as/non-null!, nouseEffect/useCallback/useMemo, no new deps), and the verification it must run (tsc, the relevant tests). Sub agents do not see this conversation. - Review every result yourself before reporting. Read the diff (
git diff), not the agent's summary. Check: design followed, banned types absent, duplication removed, comments accurate, tests meaningful. Runtscand the affected tests yourself. - Fix small review findings directly; send large ones back. A misplaced comment or a missing type annotation you fix inline. A wrong design or a missed file goes back to the same agent via
SendMessageso it keeps its context. - If a sub agent stalls or hits a spend limit, finish from the diff on disk. Do not re-run the whole task from scratch; the work that landed is usually most of it.
- Report outcomes, not process. Say what changed, what you verified, and what the sub agents got wrong that you corrected.
Before fan-out: throughput checkpoint
Write these four as todos before spawning any sub agent. A line that does not apply stays with n/a: <reason>.
- Blocking first steps. Gates that must land before parallel work (shared types, schema).
- Independent workstreams. Disjoint files, services, or layers run in parallel.
- Shared mutable state. Two agents never write the same file; split the target or serialise.
- Smallest safe decomposition. If one agent is best, say why.
Bug fixes
Every shipped line traces to runtime evidence. A change that "might help" is a hypothesis, not a fix; revert it when evidence refutes it.
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.
- 15d ago Changed · +21 lines 55c6f0b9e5a1
- 1mo ago First seen · 16 lines · 50 tokens per session scan A 8e12bb277652
fable-mode is a skill published in the GitHub repository vvedantb/eva (101 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 738 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…