jj

jj is a skill for Claude Code from tommymorgan/claude-plugins. It costs 38 tokens per session (2,198 once invoked), scanned A, original, MIT.

A guide for using Jujutsu (jj), a version-control system, in repositories that contain a .jj directory.

In plain words
What is it for?
It guides commits, branches, rebases, merges, pushes, and other repository work with jj commands while explaining them in familiar Git terms.
Why use it?
It helps avoid raw Git commands that can bypass jj's tracking and operation history, especially when a repository uses both systems.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Not installable on its own: it reads a path above its own folder, which only exists inside its repository. The line is jj workspace add ../workspace-name.

Part of the tommymorgan plugin — 10 skills, 14 commands, 13 agents, 4 hooks shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add tommymorgan/claude-plugins
Claude Code
/plugin install tommymorgan

Made for: Claude Code.

Or install tommymorgan, the plugin that ships this one along with the rest of its 10 skills, 14 commands, 13 agents, 4 hooks.

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 jj

README.md
[![agentmods](https://agentmods.dev/badge/skills/tommymorgan/claude-plugins/jj.svg)](https://agentmods.dev/skills/tommymorgan/claude-plugins/jj)
Your own site
<a href="https://agentmods.dev/skills/tommymorgan/claude-plugins/jj"><img src="https://agentmods.dev/badge/skills/tommymorgan/claude-plugins/jj.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,198 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00038 $0.02198
Opus 5 $0.00019 $0.01099
Sonnet 5 $0.00008 $0.00440
Haiku 4.5 $0.00004 $0.00220

Measured 6d ago against content hash d437ff3f4989, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

jj 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 6d 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.

tommymorgan/vcs/skills/jj/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

jj (Jujutsu VCS) Guide

When a .jj/ directory is present, the repository is managed by jj. Use jj commands for all version control operations. Never use raw git commands.

Communication Convention

Use jj commands but speak in git terminology. Since the canonical remote is typically a git repository (GitHub/GitLab), use familiar git terms when communicating:

jj term Say this instead
change commit
bookmark branch
@ (working copy) current commit / working copy
@- (parent) parent commit
describe set commit message

This keeps communication clear for all team members regardless of their jj familiarity.

Critical Safety Rules

Never use raw git commands

In a colocated jj+git repository, raw git commands bypass jj's operation log and can corrupt repository state. The following are forbidden:

  • git commit — use jj describe + jj new
  • git add — not needed, jj auto-tracks all changes
  • git checkout — use jj edit or jj new
  • git branch — use jj bookmark
  • git stash — not needed, just jj new
  • git merge — use jj new commit1 commit2 (merge commit)
  • git rebase — use jj rebase

Exception: gh CLI is acceptable (it uses git internally for PR operations).

Always create a new commit before editing pushed code

If the current commit (@) has a branch that has been pushed to the remote, do not edit files directly. This rewrites history and causes force pushes.

Instead:

  1. Run jj new to create a fresh empty commit on top
  2. Then make edits

Always pass -m to commands that open an editor

Commands like jj squash, jj split, and jj commit open an interactive editor (vim) to compose a message when no -m flag is provided. Claude Code runs in a non-interactive terminal, so the editor fails with Error reading input, exiting... and the command aborts.

Always pass -m "message" to these commands:

# ✅ GOOD — non-interactive
jj squash --from <rev> --into <rev> -m "combined commit message"
jj squash -m "squash into parent"

# ❌ BAD — opens vim, fails in non-interactive terminal
jj squash --from <rev> --into <rev>
jj squash

Read the full file on GitHub · 230 lines

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. 6d ago First seen · 230 lines · 38 tokens per session scan A d437ff3f4989

Subscribe to this mod's changes

jj is a skill published in the GitHub repository tommymorgan/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 2,198 once invoked, about $0.0002 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens