agentic-jujutsu

Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination

Install with Tessl CLI

npx tessl i github:ruvnet/agentic-flow --skill agentic-jujutsu

What are skills?

Review — 28%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 9 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

Adaptive Deployment Tracker

Trajectory lifecycle and self-learning workflow

Criteria

Without context

With context

Correct import

100%

Trajectory start called

100%

Meaningful task descriptions

100%

addToTrajectory called

100%

Finalize with honest scores

100%

Valid score range

100%

Failure recorded with critique

100%

getSuggestion JSON.parse

100%

getLearningStats JSON.parse

100%

Lifecycle ordering

100%

Output file present

100%

Without context: $0.7846 · 2m · 33 turns · 10,210 in / 6,398 out tokens

With context: $1.0209 · 2m 36s · 35 turns · 39 in / 9,177 out tokens

100%

36%

Distributed Code Analysis System

Multi-agent concurrent coordination

Criteria

Without context

With context

Concurrent execution

100%

Per-agent JjWrapper

100%

No lock-based sequencing

100%

Agent trajectory lifecycle

60%

100%

Distinct agent descriptions

100%

getSuggestion JSON.parse

100%

queryTrajectories JSON.parse

100%

Confidence logged

100%

queryTrajectories result used

100%

Output file present

100%

Without context: $3.4967 · 8m 15s · 94 turns · 274 in / 27,553 out tokens

With context: $0.5167 · 1m 29s · 25 turns · 288 in / 4,709 out tokens

65%

-1%

Artifact Integrity Verification System

Quantum security and operation tracking

Criteria

Without context

With context

Named quantum imports

Buffer input to fingerprint

verifyQuantumFingerprint usage

Tamper detection shown

80%

70%

Encryption enabled

100%

Random base64 key

100%

getUserOperations used

100%

getStats JSON.parse

100%

Output file present

100%

Without context: $0.8645 · 2m 31s · 33 turns · 39 in / 8,182 out tokens

With context: $1.1995 · 3m 22s · 39 turns · 303 in / 12,466 out tokens

Evaluated: about 13 hours ago
Agent: Claude Code

Table of Contents

Adaptive Deployment Tracker Distributed Code Analysis System Artifact Integrity Verification System

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.