working-with-jj

working-with-jj is a skill for Claude Code from YPares/agent-skills. It costs 62 tokens per session (1,798 once invoked), scanned A, original, MIT.

A guide to JJ, also called Jujutsu, a version-control system for tracking changes to code. It explains its history model, automatic working-copy snapshots, conflict handling, and command language.

In plain words
What is it for?
Use it to inspect history and diffs, select revisions or files, format log output, resolve conflicts later, undo operations, and work with Git repositories connected to JJ.
Why use it?
It helps developers work with JJ concepts that differ from Git, such as immutable change IDs, no staging area, and an operations log that can undo actions.

Skill for Claude Code

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

Part of the jujutsu-skills plugin — 2 skills shipped together

Good fit Use it to inspect history and diffs, select revisions or files, format log output, resolve conflicts later, undo operations, and work with Git repositories connected to JJ.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ypares/agent-skills/working-with-jj
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 YPares/agent-skills --skill working-with-jj
Clone the repo
git clone --depth 1 https://github.com/YPares/agent-skills

Made for: Claude Code.

Or install jujutsu-skills, the plugin that ships this one along with the rest of its 2 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 working-with-jj

README.md
[![agentmods](https://agentmods.dev/badge/skills/ypares/agent-skills/working-with-jj/github.svg)](https://agentmods.dev/skills/ypares/agent-skills/working-with-jj)
Your own site
<a href="https://agentmods.dev/skills/ypares/agent-skills/working-with-jj"><img src="https://agentmods.dev/badge/skills/ypares/agent-skills/working-with-jj/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 working-with-jj

Your own site · 80×15
<a href="https://agentmods.dev/skills/ypares/agent-skills/working-with-jj"><img src="https://agentmods.dev/badge/skills/ypares/agent-skills/working-with-jj.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,798 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00062 $0.01798
Opus 5 $0.00031 $0.00899
Sonnet 5 $0.00012 $0.00360
Haiku 4.5 $0.00006 $0.00180

Measured 12d ago against content hash 0bdb75d88bc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

working-with-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 12d 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.

working-with-jj/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

JJ (Jujutsu) Version Control Helper

Core Principles

  • Change IDs (immutable) vs Commit IDs (content-based hashes that change on edit)
  • Operations log - every operation can be undone (progressive: multiple jj undo goes further back, jj redo reverses)
  • No staging area - working copy auto-snapshots
  • Conflicts don't block - resolve later
  • Commits are lightweight - edit freely
  • Colocated by default - Git repos have both .jj and .git (since v0.34)
  • Three DSLs:
    • revsets: select across revisions - a revision (change) ID is a trivial but fully valid singleton revset
    • filesets: select across files in the repository - a regular filepath is a trivial but fully valid singleton fileset
    • templates: select which info to log and how to show it
    • Many jj commands expect expressions using either of these DSLs, to select what to show/operate on

Essential Commands

jj log -r <revset> [-p]               # View history (--patch/-p: include diffs, --count: just count)
jj log -r <revset> -G                 # -G is short for --no-graph
jj show -r <rev>                      # Show revision details (description + diff)
jj evolog -r <rev> [-p]               # View a revision's evolution
jj new [-A] <base>                    # Create revision and edit it (-A: insert between <base> and its children rather than just on top of base)
jj new --no-edit <base>               # Create without switching
jj edit <rev>                         # Switch to editing revision
jj desc -r <rev> -m "text"            # Set description
jj metaedit -r <rev> -m "text"        # Modify metadata (author, timestamps, description)

jj diff                               # Changes in @
jj diff -r <revset>                   # Changes in revset (need to be contiguous)
jj diff -f <rev1> -t <rev2>           # Differences between two states
jj file show -r <rev> <fileset>       # Show file contents at revision (without switching)
jj file show -r <rev> **/*.md -T '"=== " ++ path ++ " ===\n"'  # Multiple files with path headers
jj restore <fileset>                    # Discard changes to files
jj restore --from <commit-id> <fileset> # Restore from another revision/commit

jj split -r <rev> <paths> -m "text"   # Split into two revisions
jj absorb                             # Auto-squash changes into ancestor commits

jj rebase -s <src> -o <dest>          # Rebase with descendants onto <dest>
jj rebase -r <rev> -o <dest>          # Rebase single revision onto <dest>
# NOTE: -d/--destination is deprecated, use -o/--onto instead

jj file annotate <path>               # Blame: who changed each line
jj bisect run -- <cmd>                # Binary search for bug-introducing commit

Read the full file on GitHub · 165 lines

Files

What ships with it

6 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.

  1. 12d ago First seen · 165 lines · 62 tokens per session scan A 0bdb75d88bc0

Subscribe to this mod's changes

working-with-jj is a skill published in the GitHub repository YPares/agent-skills (30 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 1,798 once invoked, about $0.0003 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 2026-08-30.