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.
npx skills add kawaz/claude-plugin-jj --skill jj-guidegit clone --depth 1 https://github.com/kawaz/claude-plugin-jjWrote 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.
[](https://agentmods.dev/skills/kawaz/claude-plugin-jj/jj-guide)<a href="https://agentmods.dev/skills/kawaz/claude-plugin-jj/jj-guide"><img src="https://agentmods.dev/badge/skills/kawaz/claude-plugin-jj/jj-guide/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.
<a href="https://agentmods.dev/skills/kawaz/claude-plugin-jj/jj-guide"><img src="https://agentmods.dev/badge/skills/kawaz/claude-plugin-jj/jj-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00031 | $0.02064 |
| Opus 5 | $0.00015 | $0.01032 |
| Sonnet 5 | $0.00006 | $0.00413 |
| Haiku 4.5 | $0.00003 | $0.00206 |
Grade A, and why
jj-guide 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jj ガイド
基本概念
- 全変更が自動的に @ コミットに入るのが大前提（ステージング概念なし）
- @コミット ≒ 自動スナップショット機能付きワーキングツリー（編集するたびに自動amend）
jj new— 新しい空コミットを作るjj edit— 指定コミットを編集する ≒ git switch
例：
# 編集中の変更は自動的に @ に記録される
echo "content" > file.txt # 変更は即座に @ に反映
jj st # 変更を確認
# 変更を確定して次に進む
jj commit -m "Add file" # @ の変更をコミット、新しい @ を作成
# 新しいコミットを作って作業開始
jj new -m "Next feature" # 空コミットを作成して作業開始
Git → jj 対応表
| Git | jj | 備考 |
|---|---|---|
git status |
jj st |
|
git log |
jj log |
|
git diff |
jj diff |
|
git add |
不要 | 自動追跡 |
git add . && git commit -m MSG |
jj commit -m MSG |
|
git commit --amend -m MSG |
jj describe -m MSG |
メッセージ変更のみ |
git commit -m MSG |
jj describe -m MSG && jj new |
describe + new の2段階 |
git add -p && git commit |
jj split / jj commit -i |
|
git branch |
jj bookmark (jj b) |
|
git push |
jj git push |
|
git fetch/pull |
jj git fetch |
pull = fetch + rebase |
git checkout/switch |
jj new / jj edit |
new=新コミット, edit=既存編集 |
git rebase |
jj rebase |
子孫は自動追従 |
git stash |
不要 | 作業内容は自動で@に保存 |
git cherry-pick |
jj duplicate |
--ontoで挿入先指定可 |
git revert |
jj revert |
挿入先指定が必須(--onto/-A/-B) |
git reset --hard HEAD~1 |
jj abandon |
コミット破棄 |
git reflog |
jj op log |
操作ログ |
git blame FILE |
jj file annotate FILE |
|
git grep PATTERN |
jj file search PATTERN |
|
git restore -- FILE |
jj restore FILE |
--from @- が省略時デフォルト |
git bisect |
jj bisect run CMD |
自動bisectのみ |
jj 固有コマンド
| コマンド | 概要 |
|---|---|
jj absorb |
@の変更をhunk単位で祖先コミットへ自動分配 |
jj evolog |
changeの変遷履歴 |
jj parallelize |
直列コミットを並列（兄弟）に変換 |
jj metaedit |
内容を変えずメタデータだけ変更 |
jj diffedit |
diff editorでコミット内容を直接編集 |
jj fix |
設定済みフォーマッタを一括適用 |
ワークスペース
jj workspace list # ワークスペース一覧
jj workspace add --name NAME PATH # 新規ワークスペース作成
jj workspace forget NAME # ワークスペース削除（引数なし=default削除なので注意）
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.
- 9d ago First seen · 181 lines · 31 tokens per session scan A 32aecbf4cbf5
jj-guide is a skill published in the GitHub repository kawaz/claude-plugin-jj (6 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 2,064 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.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…