agentic-jujutsu
Coordinate AI Agents with Agentic Jujutsu
Concurrent AI agents can create conflicting changes and repeat failed workflows. This skill documents Agentic Jujutsu methods for coordination, trajectory learning, and integrity checks.
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "agentic-jujutsu" from https://skillstore.io/skills/ruvnet-agentic-jujutsu.md and its manifest at https://skillstore.io/api/skills/ruvnet-agentic-jujutsu/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "agentic-jujutsu". Inspect this repository without making changes.
Expected outcome:
The repository status is summarized. No commit, branch, rebase, installation, or network action is performed.
Using "agentic-jujutsu". Summarize learning after ten completed trajectories.
Expected outcome:
The summary covers trajectory count, patterns, average success, improvement rate, prediction accuracy, and low-confidence areas.
Using "agentic-jujutsu". Plan concurrent work for three agents.
Expected outcome:
Three independent work areas are proposed, with overlap checks, branch ownership, and a review checkpoint before commits.
Security Audit
High RiskMost external-command alerts are false positives caused by Markdown fences, JavaScript template literals, and inline code. The setup command executes an NPM package, while examples automatically execute learned recommendations and record complete command strings. Publication should require safeguards for package installation, operation approval, and command-log redaction.
Confirmed security concerns (2)
Capability review items (1)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
⚙️ External commands (50)
🌐 Network access (2)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/ruvnet-agentic-jujutsu/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/ruvnet-agentic-jujutsu?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/ruvnet-agentic-jujutsu?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/ruvnet-agentic-jujutsu/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/ruvnet-agentic-jujutsu.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
ruvnet. (2026). agentic-jujutsu security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/ruvnet-agentic-jujutsu/audits/8BibTeX citation
@techreport{ruvnet-ruvnet-agentic-jujutsu-2026,
author = {ruvnet},
title = {agentic-jujutsu security audit report (audit version 8)},
institution = {Skillstore},
year = {2026},
number = {8},
url = {https://skillstore.io/skills/ruvnet-agentic-jujutsu/audits/8},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "agentic-jujutsu security audit report (audit version 8)"
version: "unspecified"
type: report
authors:
- name: "ruvnet"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/ruvnet-agentic-jujutsu/audits/8"
identifiers:
- type: other
value: "skillstore:ruvnet-agentic-jujutsu:audit:8"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Coordinate Concurrent Development
Coordinate independent code changes across multiple AI agents while recording outcomes for later workflow suggestions.
Improve Deployment Workflows
Track deployment trajectories, compare prior outcomes, and review suggested operations before running them.
Check Repository Integrity
Generate integrity fingerprints and evaluate encryption workflows without assuming documented guarantees are independently verified.
Try These Prompts
Use Agentic Jujutsu to inspect this repository and summarize status. Do not modify files or run installation commands without approval.
Track my task as a trajectory, record relevant version-control operations, and ask for an honest outcome score before finalizing.
Plan independent branches for three agents, identify overlap, and propose a concurrent commit sequence using Agentic Jujutsu.
Review ReasoningBank recommendations for this deployment. Validate every operation, flag destructive steps, and request approval before execution.
Best Practices
- Use specific task descriptions and record honest outcome scores with concise critiques.
- Review learned suggestions against repository state and require approval before destructive or networked operations.
- Redact secrets from commands and trajectory context before storing operation history.
Avoid
- Do not execute unpinned external packages without verifying provenance and obtaining approval.
- Do not run learned operations automatically or treat confidence scores as authorization.
- Do not inflate success scores or omit failures, because distorted trajectories weaken later suggestions.