agentic-jujutsu

agentic-jujutsu is a skill for Claude Code from frankxai/claude-skills-library. It costs 57 tokens per session (1,781 once invoked), scanned A, original, MIT.

A version-control system for AI agents that combines quantum-resistant protection, learning from past work, and coordination between agents. Version control records changes so work can be reviewed or restored.

In plain words
What is it for?
Designing agent memory and versioning, coordinating agents over shared state, and building experience-replay or learning loops.
Why use it?
It addresses shared state, history, and learning needs when several AI agents modify or build on the same work.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-skills-library plugin — 114 skills shipped together

Good fit Designing agent memory and versioning, coordinating agents over shared state, and building experience-replay or learning loops.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/frankxai/claude-skills-library/agentic-jujutsu
Install

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.

Any agent
npx skills add frankxai/claude-skills-library --skill agentic-jujutsu
Clone the repo
git clone --depth 1 https://github.com/frankxai/claude-skills-library

Made for: Claude Code.

Or install claude-skills-library, the plugin that ships this one along with the rest of its 114 skills.

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 agentic-jujutsu

README.md
[![agentmods](https://agentmods.dev/badge/skills/frankxai/claude-skills-library/agentic-jujutsu/github.svg)](https://agentmods.dev/skills/frankxai/claude-skills-library/agentic-jujutsu)
Your own site
<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/agentic-jujutsu"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/agentic-jujutsu/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.

agentmods 80×15 button for agentic-jujutsu

Your own site · 80×15
<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/agentic-jujutsu"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/agentic-jujutsu.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,781 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00057 $0.01781
Opus 5.5 $0.00023 $0.00712
Sonnet 5.5 $0.00011 $0.00356
Haiku 4.5 $0.00006 $0.00178

Measured 1mo ago against content hash 1b1af7c4044d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentic-jujutsu 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 1mo 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.

free-skills/agentic-jujutsu/SKILL.md · 282 lines

How it starts

The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Jujutsu - AI Agent Version Control

Quantum-ready, self-learning version control designed for multiple AI agents working simultaneously without conflicts.

When to Use This Skill

Use agentic-jujutsu when you need:

  • ✅ Multiple AI agents modifying code simultaneously
  • ✅ Lock-free version control (23x faster than Git)
  • ✅ Self-learning AI that improves from experience
  • ✅ Quantum-resistant security for future-proof protection
  • ✅ Automatic conflict resolution (87% success rate)
  • ✅ Pattern recognition and intelligent suggestions
  • ✅ Multi-agent coordination without blocking

Quick Start

Installation

npx agentic-jujutsu

Basic Usage

const { JjWrapper } = require('agentic-jujutsu');

const jj = new JjWrapper();

// Basic operations
await jj.status();
await jj.newCommit('Add feature');
await jj.log(10);

// Self-learning trajectory
const id = jj.startTrajectory('Implement authentication');
await jj.branchCreate('feature/auth');
await jj.newCommit('Add auth');
jj.addToTrajectory();
jj.finalizeTrajectory(0.9, 'Clean implementation');

// Get AI suggestions
const suggestion = JSON.parse(jj.getSuggestion('Add logout feature'));
console.log(`Confidence: ${suggestion.confidence}`);

Reference

The full detail lives in references/ and loads only when needed:


Best Practices

1. Trajectory Management

// ✅ Good: Meaningful task descriptions
jj.startTrajectory('Implement user authentication with JWT');

// ❌ Bad: Vague descriptions
jj.startTrajectory('fix stuff');

// ✅ Good: Honest success scores
jj.finalizeTrajectory(0.7, 'Works but needs refactoring');

// ❌ Bad: Always 1.0
jj.finalizeTrajectory(1.0, 'Perfect!'); // Prevents learning

2. Pattern Recognition

// ✅ Good: Let patterns emerge naturally
for (let i = 0; i < 10; i++) {
    jj.startTrajectory('Deploy feature');
    await deploy();
    jj.addToTrajectory();
    jj.finalizeTrajectory(wasSuccessful ? 0.9 : 0.5);
}

// ❌ Bad: Not recording outcomes
await deploy(); // No learning

Read the full file on GitHub · 282 lines

Files

What ships with it

1 file 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.

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. 1mo ago First seen · 282 lines · 57 tokens per session scan A 1b1af7c4044d

Subscribe to this mod's changes

agentic-jujutsu is a skill published in the GitHub repository frankxai/claude-skills-library (47 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 1,781 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 2026-08-30.