A reference guide for advanced Jujutsu, or jj, version-control tasks. It covers conflicts, operation history, bookmarks, revision sets, pull-request workflows, and repository configuration.

Use it when investigating jj conflicts, reviewing its operation log, managing bookmarks or multiple remotes, working with Git repositories, or using fileset patterns.

It provides guidance for jj situations beyond the everyday workflow, including commands whose details may change between versions.

advanced-jj — Skill for Claude Code and Codex by martinemde: A reference guide for advanced Jujutsu, or jj, version-control…

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.

agentmods

npx agentmods add skills/martinemde/dotfiles/advanced-jj

Any agent

npx skills add martinemde/dotfiles --skill advanced-jj

Clone the repo

git clone --depth 1 https://github.com/martinemde/dotfiles

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/martinemde/dotfiles/advanced-jj.svg)](https://agentmods.dev/skills/martinemde/dotfiles/advanced-jj)

Your own site

<a href="https://agentmods.dev/skills/martinemde/dotfiles/advanced-jj"><img src="https://agentmods.dev/badge/skills/martinemde/dotfiles/advanced-jj.svg" alt="Measured on agentmods" height="20"></a>

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 777 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.

Model	Per session	Once invoked
Fable 5.1	$0.00081	$0.00777
Opus 5	$0.00041	$0.00388
Sonnet 5	$0.00016	$0.00155
Haiku 4.5	$0.00008	$0.00078

Measured 5d ago against content hash 482ce4af2819, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

advanced-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 5d 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.

home/dot_claude/skills/advanced-jj/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Advanced Jujutsu (jj)

The everyday flow and safety rules live in CLAUDE.md; describing and splitting changes lives in the commit skill. This is the deeper reference for what neither of those covers.

jj's CLI moves faster than these notes, so verify against jj --help and jj <command> --help before acting. Treat this skill as orientation, not ground truth.

Mental Model

@ — the working copy (current change)
@- — parent of @
Changes auto-amend: editing files updates @ in place, no staging
jj squash folds @ into its parent (--into <rev> targets any ancestor)

Diffs with Filesets

jj show does not accept path arguments — use jj diff. Filesets support glob and set operations:

jj diff -r @-                                     # full parent diff
jj diff -r @- path/to/file                        # one file
jj diff -- 'glob:"bin/*" ~ glob:"bin/,special"'   # glob minus exclusion

Non-interactive Split

jj split -i needs an editor. For scripted splits, use --tool true — the true command exits 0, accepting the file list as given:

jj split --tool true -m "Extract feature" -- \
  'glob:"path/to/file1"' 'glob:"path/to/file2"'

Remaining changes stay in a follow-up working copy change.

Fixing an Earlier Change

Don't rewrite an earlier change in place. Build the fix on top of it, then fold it in:

jj new <target>                              # new change on top of the target
# make the fix
jj squash --into <target> --tool true        # fold it back, no diff editor

Advancing Bookmarks

After finalizing work, move the nearest ancestor bookmark forward:

jj bookmark advance                  # closest bookmark(s) → @

See jj bookmark advance --help for --to and other targeting.

Reference Files

Load from references/ as needed:

git-to-jj-commands.md — Git → jj command translation table
git-comparison.md — Conceptual differences from Git
git-compatibility.md — Colocated repos, Git interop
working-copy.md — How automatic commits work
bookmarks.md — Managing bookmarks (branches)
revsets.md — Query syntax (@, @-, main..@, etc.)
conflicts.md — Conflict resolution
operation-log.md — jj op log, undo, restore
divergence.md — Handling divergent changes
github.md — Fork workflows and PRs
multiple-remotes.md — Multi-remote setups
config.md — Configuration options
tutorial.md — Step-by-step introduction (for humans)

Read the full file on GitHub · 90 lines

Files

What ships with it

13 files 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.

5d ago First seen · 90 lines · 81 tokens per session scan A 482ce4af2819

Subscribe to this mod's changes

advanced-jj is a skill published in the GitHub repository martinemde/dotfiles (9 stars, last pushed 5d ago), licensed ISC. It adds 81 tokens to every session and 777 once invoked, about $0.0004 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.

Git and workflow chezmoi claude-code dotfiles jj

dotfiles-bootstrap

Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.

sebastienrousseau/dotfiles · 88 tokens

vibe

Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…

sebastienrousseau/dotfiles · 137 tokens

aiq-research

Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.

laurigates/dotfiles · 25 tokens

obsidian-bases

Obsidian Bases database feature for YAML-based interactive note views. Use when creating .base files, writing filter queries, building formulas, configuring table/card views, or working with Obsidian properties and frontmatter databases.

laurigates/dotfiles · 49 tokens

Send notifications, interactive questions, or multiple-choice polls to the user via Telegram. Use when the user asks to be notified ("ping me", "notify me on Telegram", "ask me when..."), when a long-running task finishes and the user is likely away, when an irreversible action needs out-of-band confirmation, or when…

laurigates/dotfiles · 117 tokens

chezmoi-expert

Comprehensive chezmoi dotfiles management expertise including templates, cross-platform configuration, file naming conventions, and troubleshooting. Covers source directory management, reproducible environment setup, and chezmoi templating with Go templates. Use when user mentions chezmoi, dotfiles, cross-platform…

laurigates/dotfiles · 88 tokens

advanced-jj