jjj

jjj is a skill for Claude Code, Codex from doug/jjj. It costs 40 tokens per session (1,644 once invoked), scanned A, original, Apache-2.0.

A project-management and code-review system for Jujutsu repositories, a version-control system similar to Git.

In plain words
What is it for?
Use it to track problems, link solutions to Jujutsu change IDs, record critiques, find file overlaps, review status, and synchronise metadata.
Why use it?
It keeps problems, proposed solutions, and review comments connected to code changes even when the project history is rewritten.

Skill for Claude CodeCodex

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/doug/jjj/public
Any agent
npx skills add doug/jjj --skill public
Clone the repo
git clone --depth 1 https://github.com/doug/jjj

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.

agentmods badge for jjj

README.md
[![agentmods](https://agentmods.dev/badge/skills/doug/jjj/public.svg)](https://agentmods.dev/skills/doug/jjj/public)
Your own site
<a href="https://agentmods.dev/skills/doug/jjj/public"><img src="https://agentmods.dev/badge/skills/doug/jjj/public.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,644 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 $0.00040 $0.01644
Opus 5 $0.00020 $0.00822
Sonnet 5 $0.00008 $0.00329
Haiku 4.5 $0.00004 $0.00164

Measured 4d ago against content hash 3d976305c619, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jjj 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 4d 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.

docs-site/public/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

jjj (Jujutsu Juggler)

Distributed project management and code review built on Jujutsu. No server, no database — metadata lives in an orphaned jjj bookmark and syncs with jj git push/pull.

Key insight: Jujutsu's stable Change IDs survive rebases and squashes, so metadata stays attached to work even after history rewrites.

Core Model

Problems → Solutions → Critiques
   │           │           │
   │           │           └── Error elimination (blocks approval)
   │           └── Conjectures linked to jj Change IDs
   └── Things that need solving (can nest via --parent)

State machines:

  • Problems: openin_progresssolved / dissolved
  • Solutions: proposedsubmittedapproved / withdrawn
  • Critiques: openaddressed / validated / dismissed

Quick Reference

Task Command
Initialize jjj init
Status jjj status
Next action jjj next [--top N] [--mine] [--claim]
Interactive TUI jjj ui
Sync jjj push / jjj fetch / jjj sync
Full-text search jjj search "query"
Timeline jjj timeline "title"
File overlaps jjj overlaps
Project insights jjj insights

Problems

Task Command
Create jjj problem new "Title" [--priority critical|high|medium|low]
List jjj problem list [--status open|in_progress|solved|dissolved]
Show jjj problem show "title or id"
Tree view jjj problem tree
Edit jjj problem edit "title" --title "New" --priority high
Solve jjj problem solve "title"
Dissolve jjj problem dissolve "title" --reason "..."
Reopen jjj problem reopen "title"
Sub-problem jjj problem new "Sub" --parent "parent title"
Assign jjj problem assign "title" --to [email protected]

Solutions

Task Command
Create jjj solution new "Title" --problem "title or id"
List jjj solution list [--problem "title"] [--status proposed]
Submit for review jjj solution submit "title"
Approve jjj solution approve "title" [--rationale "..."] [--force]
Withdraw jjj solution withdraw "title" --rationale "..."
Assign jjj solution assign "title" --to [email protected]

Read the full file on GitHub · 173 lines

Files

What ships with it

9 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. 4d ago First seen · 173 lines · 40 tokens per session scan A 3d976305c619

Subscribe to this mod's changes

jjj is a skill published in the GitHub repository doug/jjj (12 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,644 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 2026-08-30.

Related

Other skills, from other repositories