eva: Skill for Claude Code

.claude/skills/fable-mode/SKILL.md

fable-mode is a skill for Claude Code from vvedantb/eva. It costs 50 tokens per session (409 once invoked), scanned A, original, MIT.

A coding-agent workflow where the main agent plans and reviews while Opus sub-agents implement the changes. Opus is a model used for delegated coding work.

In plain words
What is it for?
Use it to split backend, frontend, or test work into parallel tasks, delegate edits, inspect the resulting diff, and run verification.
Why use it?
It separates planning and review from implementation, while keeping the final checks with the main agent.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is vvedantb/eva's own configuration. It tells Claude Code how to work on eva itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything eva configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/vvedantb/eva/main/.claude/skills/fable-mode/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vvedantb/eva

Made for: Claude Code.

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-mode

README.md
[![agentmods](https://agentmods.dev/badge/skills/vvedantb/eva/fable-mode.svg)](https://agentmods.dev/skills/vvedantb/eva/fable-mode)
Your own site
<a href="https://agentmods.dev/skills/vvedantb/eva/fable-mode"><img src="https://agentmods.dev/badge/skills/vvedantb/eva/fable-mode.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 409 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 5.1 $0.00050 $0.00409
Opus 5 $0.00025 $0.00204
Sonnet 5 $0.00010 $0.00082
Haiku 4.5 $0.00005 $0.00041

Measured 3d ago against content hash 8e12bb277652, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 3d 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-mode/SKILL.md · 16 lines

What it actually says

Fable mode: you plan and review, Opus sub agents implement.

Rules

  1. You never edit source files directly. Every code change goes through an Agent call with model: "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.
  2. 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 !, no useEffect/useCallback/useMemo, no new deps), and the verification it must run (tsc, the relevant tests). Sub agents do not see this conversation.
  3. 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. Run tsc and the affected tests yourself.
  4. 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 SendMessage so it keeps its context.
  5. 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.
  6. Report outcomes, not process. Say what changed, what you verified, and what the sub agents got wrong that you corrected.
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. 3d ago First seen · 16 lines · 50 tokens per session scan A 8e12bb277652

Subscribe to this mod's changes

fable-mode is a skill published in the GitHub repository vvedantb/eva (101 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 409 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens