Agent skill

Bunshin

by AThevon in AThevon/genjutsu

Summon shadow clones: genjutsu's full-scale pipeline for a whole website or web app, from scratch or as a full redesign.

Custom licenceAuto-check: notesAgent Workflows

Install Bunshin

skills CLI
$ npx skills add AThevon/genjutsu --skill bunshin -a claude-code

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

GitHub CLI
$ gh skill install AThevon/genjutsu bunshin --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/AThevon/genjutsu.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/bunshin .claude/skills/bunshin && 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
bunshin
GitHub stars
431
Token cost
~16k tokens
SKILL.md length
7,878 words
Files
1
Skills in repo
20
Repo updated
First seen
Licence
Custom licence

At a glance

Summon shadow clones: genjutsu's full-scale pipeline for a whole website or web app, from scratch or as a full redesign.

  • Works in 12 steps: READ - the project, the brief, the host → SUMMON - the first gate → HARVEST - the real material → …
  • Tasks that involve Subagents
  • SKILL.md covers Voice, bunshin, paint, cast, Iron Rules and Step down, when this is not…, plus 9 more sections
  • Calls python3, npx and node; reaches genjutsu.athevon.dev

What it does

Bunshin is an agent skill from AThevon/genjutsu. Summon shadow clones: genjutsu's full-scale pipeline for a whole website or web app, from scratch or as a full redesign. Harvests the client's real material, researches in parallel, lets Impeccable lead the direction and genjutsu the motion, builds the pages with parallel agents, then loops fixes, verdicts and a cold-eyes art director until only minor issues remain, the round cap of the chosen tier is reached, or a round fixes nothing. Announces its cost first and asks twice. Web. Needs a host that can spawn…

Its SKILL.md is about 16k 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: Creative coding skills for Claude Code, claude.ai and Cowork. Motion, micro-interactions and design systems across Web (GSAP, Motion, Three.js, CSS), Android (Jetpack Compose)…

When your agent uses it

  • Tasks that involve Subagents

Example prompts

  • “/bunshin”

Requirements

  • Python 3
  • Node.js
  • Pre-approved tools (allowed-tools): Bash, Read, Edit, Write, Grep, Glob, WebSearch, WebFetch, Artifact, Agent, Workflow, AskUserQuestion, Skill

Workflow steps

12 steps, taken from the step headings in SKILL.md.

  1. READ - the project, the brief, the host
  2. SUMMON - the first gate
  3. HARVEST - the real material
  4. RESEARCH - four clones, then a synthesis
  5. DIRECTION - the second gate
  6. MATERIAL - by evidence, not by reflex
  7. FOUNDATION - yours, not a clone's
  8. CLONES - the pages, in parallel
  9. PROVE - before anyone reviews
  10. REVIEW - independent lenses
  11. REFINE - the loop
  12. SEAL - document, audit, report

What it can do on your machine

Read from SKILL.md and the folder at commit 1f518a7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Edit
    • Write
    • Grep
    • Glob
    • WebSearch
    • WebFetch
    • Artifact
    • Agent

    …and 3 more on the same allowed-tools line.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3
    • npx
    • node
    • rsync
    • git

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • genjutsu.athevon.dev

    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

Bunshin loads about 16k tokens when it runs. Until then it costs about 133 tokens; SKILL.md has 7,878 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~133
When it runs · the whole SKILL.md, loaded when a task matches
~16k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Edit, Write, Grep, Glob, WebSearch, WebFetch, Artifact, Agent, Workflow, AskUserQuestion

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 7,878 words (~16,098 tokens).

“You direct. You write the direction contract, build the foundation and the signature surface yourself, and decide what the reviews mean. Clones (subagents) research, build pages in parallel on files that never overlap, review through independent lenses, and apply the…”

— opening of SKILL.md by AThevon, Custom licence
name
bunshin
allowed-tools
Bash, Read, Edit, Write, Grep, Glob, WebSearch, WebFetch, Artifact, Agent, Workflow, AskUserQuestion, Skill

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/bunshin of AThevon/genjutsu.

Open the folder on GitHubat commit 1f518a7

Compare with similar skills

Bunshin 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.

Bunshin compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bunshin this skillAThevon/genjutsu431—~16kAutomated safety check: NotesCustom licence
Claude Code Agent Developmentanthropics/claude-plugins-official38k7 repos~2.8kAutomated safety check: PassApache-2.0
Subagent Driven DevelopmentAsvarox/allkaraoke26137 repos~1.2kAutomated safety check: PassNone
Dispatching Parallel Agentsultralisp/ultralisp25840 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 7 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 37 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 40 repos~1.5k tokens
    Agent WorkflowsAuto-check passed
  • 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 AThevon/genjutsu

All 20 skills in this repo
  • Orchestration

    AThevon/genjutsu

    Running a team of subagents on one design build: clone briefs, disjoint file ownership, isolated builds, the evidence packet, review lenses, the fix plan, verdicts, cold eyes and the stop rule, with…

    431 GitHub stars~4.9k tokensUpdated 4 days ago
    Auto-check passed
  • Design Audit

    AThevon/genjutsu

    Design audit checklist - motion gaps, accessibility, color consistency, responsive, performance.

    431 GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed
  • UI UX Pro Max

    AThevon/genjutsu

    UI/UX design-system intelligence - 84 styles, 192 palettes, 74 font pairings, 25 charts, 99 UX guidelines across 22 stacks (searchable dataset + CLI).

    431 GitHub stars~4.3k tokensUpdated 4 days ago
    Auto-check passed
  • Canvas Generative

    AThevon/genjutsu

    Algorithmic and generative art with Canvas 2D - particles, flow fields, noise, fractals, L-systems.

    431 GitHub starsUsed in 1 repo~2.1k tokens
    Auto-check passed
  • Compose Motion

    AThevon/genjutsu

    Jetpack Compose animation foundations - animateAsState, AnimatedVisibility, Crossfade, updateTransition, SharedTransitionLayout, gestures.

    431 GitHub starsUsed in 1 repo~3.5k tokens
    Auto-check passed
  • Compose Multiplatform

    AThevon/genjutsu

    Compose Multiplatform / KMP patterns - expect/actual composables, platform-specific code, density and font handling cross-target, iOS/Android/Desktop interop.

    431 GitHub starsUsed in 1 repo~4.1k tokens
    Auto-check passed

Categories

Questions about Bunshin

What does Bunshin do?

Summon shadow clones: genjutsu's full-scale pipeline for a whole website or web app, from scratch or as a full redesign. Bunshin is an agent skill from AThevon/genjutsu. Summon shadow clones: genjutsu's full-scale pipeline for a whole website or web app, from scratch or as a full redesign.

When should I use Bunshin?

Bunshin fits situations like: tasks that involve Subagents.

How do I install Bunshin in Claude Code?

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

How do I install Bunshin in Codex?

Run `npx skills add AThevon/genjutsu --skill bunshin -a codex`. Or copy the skill folder (skills/bunshin in AThevon/genjutsu) into .agents/skills/bunshin in your project. Codex loads it when a task matches its description.

Can I use Bunshin 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 AThevon/genjutsu --skill bunshin -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bunshin, .gemini/skills/bunshin, .github/skills/bunshin and .opencode/skills/bunshin in your project.

What does Bunshin need to run?

Going by SKILL.md and its folder, Bunshin needs the command-line tools its instructions call (python3, npx, node, rsync and git). Our summary lists: Python 3; Node.js. Its frontmatter pre-approves these tools: Bash, Read, Edit, Write, Grep, Glob, WebSearch, WebFetch, Artifact, Agent, Workflow, AskUserQuestion, Skill.

Does Bunshin access the network?

SKILL.md names 1 domain. In commands or code: genjutsu.athevon.dev; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Bunshin safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Bunshin use?

Bunshin has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Bunshin use?

About 16k tokens (SKILL.md is roughly 64k 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 Bunshin?

Skills that share tags, products or a category with Bunshin: 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 Bunshin?

AThevon (a GitHub user) maintains it in AThevon/genjutsu, which has 431 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 5, 2026.

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