New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Fable Mode

by vvedantb in vvedantb/eva

Delegate all implementation to Opus sub agents, then review their output yourself.

MITAuto-check passedAgent Workflows

Install Fable Mode

skills CLI
$ npx skills add vvedantb/eva --skill fable-mode -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install vvedantb/eva fable-mode --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/vvedantb/eva.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/fable-mode .claude/skills/fable-mode && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
fable-mode
GitHub stars
101
Token cost
~790 tokens
SKILL.md length
448 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

Delegate all implementation to Opus sub agents, then review their output yourself.

  • Works in 6 steps: You never edit source files directly.… → Brief each sub agent fully. The prompt… → Review every result yourself before… → …
  • The user says fable mode
  • SKILL.md covers Rules, Before fan-out: throughput… and Bug fixes
  • Calls git

What it does

Fable Mode is an agent skill from vvedantb/eva. Delegate all implementation to Opus sub agents, then review their output yourself. Use when the user says "fable mode", "delegate to opus", or wants the main agent to plan and review while sub agents write the code.

Its SKILL.md is about 790 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Subagents. The repository describes itself as: Orchestrate sandboxed agents that run in the cloud while you work. The licence is MIT.

When your agent uses it

  • The user says fable mode
  • Delegate to opus
  • Wants the main agent to plan and review while sub agents write the code

Example prompts

  • “fable mode”
  • “delegate to opus”
  • “/fable-mode”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. You never edit source files directly. Every code change goes through an Agent call with model: "opus". Split the work into independent…
  2. Brief each sub agent fully. The prompt must include: the exact files to touch, the agreed design (types, function names, behaviour), the…
  3. Review every result yourself before reporting. Read the diff (git diff), not the agent's summary. Check: design followed, banned types…
  4. Fix small review findings directly; send large ones back. A misplaced comment or a missing type annotation you fix inline. A wrong design…
  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…
  6. Report outcomes, not process. Say what changed, what you verified, and what the sub agents got wrong that you corrected.

What it can do on your machine

Read from SKILL.md and the folder at commit a5a4df2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Fable Mode loads about 790 tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 448 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~790

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from vvedantb/eva at commit a5a4df2, republished under its MIT licence (© vvedantb). 448 words, ~790 tokens.

Download SKILL.mdSave it as .claude/skills/fable-mode/SKILL.md (or your agent's skills folder).
name
fable-mode
description
Delegate all implementation to Opus sub agents, then review their output yourself. Use when the user says "fable mode", "delegate to opus", or wants the main agent to plan and review while sub agents write the code.

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.
Show full SKILL.md (214 more words)Show less

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.

  1. Reproduce it yourself on the real surface (agent-browser, Convex CLI, Eva MCP prod logs). A bug you cannot reproduce, you cannot prove fixed.
  2. Binary-search the cause. List hypotheses, rule them out with logs or instrumentation, and confirm the surviving mechanism before planning the fix. Apply principle-fix-root-causes.
  3. Delegate the smallest fix the evidence justifies, then review the diff.
  4. Verify on the same surface. The original repro now passes. "Inconclusive" or a different surface is not a pass; say so.
  5. Land the failing repro before the fix when a cheap test exists, so history shows red then green (principle-sequence-verifiable-units).

Report what was broken, the root cause, the fix, and the before/after repro output.

© vvedantb, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/fable-mode of vvedantb/eva.

Open the folder on GitHubat commit a5a4df2

Compare with similar skills

Fable Mode next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Fable Mode compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fable Mode this skillvvedantb/eva101—~790Automated safety check: PassMIT
Claude Code Agent Developmentanthropics/claude-plugins-official38k8 repos~2.8kAutomated safety check: PassApache-2.0
Subagent Driven DevelopmentAsvarox/allkaraoke26138 repos~1.2kAutomated safety check: PassNone
Dispatching Parallel Agentsultralisp/ultralisp25841 repos~1.5kAutomated safety check: PassNone
Paseo Advisor Second Opiniongetpaseo/paseo20k1 repos~756Automated safety check: PassCustom licence
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~12kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 8 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

  • Subagent Driven Development

    Asvarox/allkaraoke

    A skill your agent uses when executing implementation plans with independent tasks in the current session

    261 GitHub starsUsed in 38 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • Dispatching Parallel Agents

    ultralisp/ultralisp

    A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    258 GitHub starsUsed in 41 repos~1.5k tokens
    Agent WorkflowsAuto-check passed

  • Paseo Advisor Second Opinion

    getpaseo/paseo

    Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed

  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-check passed

  • O2 Review Loop

    openobserve/openobserve

    Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

    22k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from vvedantb/eva

All 23 skills in this repo

  • Eva Feature Demo

    vvedantb/eva

    Record a real agent-browser screencast of one eva feature being used end to end, convert it to an X-ready mp4, and write a tweet for it.

    101 GitHub stars~3.3k tokensUpdated today
    Auto-check passed

  • Animate

    vvedantb/eva

    Build an animation from scratch, making the decisions in the order that determines whether it feels right — should it animate at all, what purpose, which tool, which properties, which curve and…

    101 GitHub starsUsed in 6 repos~2.9k tokens
    Auto-check passed

  • Convex Create Component

    vvedantb/eva

    Design and build Convex components with clear boundaries, isolated state, and app-facing wrappers.

    101 GitHub stars~3.3k tokensUpdated today
    Auto-check passed

  • Eva Feature Screenshot

    vvedantb/eva

    Grab a single clean HD screenshot of a new eva feature from the real running app (Playwright at deviceScaleFactor 2, 1280 layout captured crisp at 2560×1440, dev overlays hidden) and write a tweet…

    101 GitHub stars~3.2k tokensUpdated today
    Auto-check: notes

  • Code Structure

    vvedantb/eva

    A skill your agent uses when multiple workflows duplicate the same operational logic, when deciding what belongs in actions vs shared services, or when refactoring repeated operational blocks across…

    101 GitHub starsUsed in 2 repos~1.1k tokens
    Auto-check passed

  • Eva Launch Video

    vvedantb/eva

    Produce polished, mobile-friendly product demo videos of the eva app with Remotion — 1280×720, snappy beat-synced hard cuts, lo-fi music that swells on every cut, and footage captured from the REAL…

    101 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

Categories

Questions about Fable Mode

What does Fable Mode do?

Delegate all implementation to Opus sub agents, then review their output yourself. Fable Mode is an agent skill from vvedantb/eva. Delegate all implementation to Opus sub agents, then review their output yourself.

When should I use Fable Mode?

Fable Mode fits situations like: the user says fable mode; delegate to opus; wants the main agent to plan and review while sub agents write the code.

How do I install Fable Mode in Claude Code?

Run `npx skills add vvedantb/eva --skill fable-mode -a claude-code`. Or copy the skill folder (.claude/skills/fable-mode in vvedantb/eva) into .claude/skills/fable-mode in your project. Claude Code loads it when a task matches its description.

How do I install Fable Mode in Codex?

Run `npx skills add vvedantb/eva --skill fable-mode -a codex`. Or copy the skill folder (.claude/skills/fable-mode in vvedantb/eva) into .agents/skills/fable-mode in your project. Codex loads it when a task matches its description.

Can I use Fable Mode in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vvedantb/eva --skill fable-mode -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fable-mode, .gemini/skills/fable-mode, .github/skills/fable-mode and .opencode/skills/fable-mode in your project.

What does Fable Mode need to run?

Going by SKILL.md and its folder, Fable Mode needs the command-line tools its instructions call (git).

Does Fable Mode access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Fable Mode safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Fable Mode use?

Fable Mode is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Fable Mode use?

About 790 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Fable Mode?

Skills that share tags, products or a category with Fable Mode: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fable Mode?

vvedantb (a GitHub user) maintains it in vvedantb/eva, which has 101 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 8, 2026.

Source: vvedantb/eva on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.