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 agentmods add commands/tommymorgan/claude-plugins/jj-setupgit clone --depth 1 https://github.com/tommymorgan/claude-pluginsWrote 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/commands/tommymorgan/claude-plugins/jj-setup)<a href="https://agentmods.dev/commands/tommymorgan/claude-plugins/jj-setup"><img src="https://agentmods.dev/badge/commands/tommymorgan/claude-plugins/jj-setup.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.01070 |
| Opus 5 | $0.00010 | $0.00535 |
| Sonnet 5 | $0.00004 | $0.00214 |
| Haiku 4.5 | $0.00002 | $0.00107 |
Grade A, and why
tommymorgan:jj-setup scanned grade A with 1 finding 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 3d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/settings.json 2>/dev/null | grep -A5 "PreToolUse" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set Up jj Safety Checks
Audit the current repository for jj usage and set up safeguards to prevent accidental git commands.
Workflow
Step 1: Verify jj Environment
Check that jj is available and the repository is jj-managed:
# Check jj is in PATH
which jj || echo "NOT_FOUND"
# Check .jj directory exists
ls -d .jj 2>/dev/null || echo "NOT_JJ_REPO"
If jj is not found: Tell the user to install jj and stop. If .jj/ doesn't exist: Tell the user this isn't a jj repo and stop.
Step 2: Check for Colocated Git
# Check if this is a colocated jj+git repo
ls -d .git 2>/dev/null && echo "COLOCATED" || echo "PURE_JJ"
If colocated, the risk of accidental git commands is highest. All subsequent checks are especially important.
Step 3: Audit CLAUDE.md
Check if the project's CLAUDE.md mentions jj:
grep -i "jj\|jujutsu" CLAUDE.md 2>/dev/null
If no mention found, add a section to CLAUDE.md:
## Version Control
This repository uses [Jujutsu (jj)](https://martinvonz.github.io/jj/) for version control. **Always use jj commands, never raw git commands.** See the `jj` skill for the full command reference.
Key rules:
- `jj status` not `git status`
- `jj describe -m "..."` + `jj new` not `git commit`
- `jj bookmark set <name>` not `git branch`
- `jj git push` not `git push`
- `jj git fetch` not `git fetch`
If already mentioned, report what's there and skip.
Step 4: Audit Claude Code Settings for Git-Blocking Hook
Check if there's a PreToolUse hook that blocks git commands in Bash:
# Check project-level settings
cat .claude/settings.json 2>/dev/null | grep -A5 "PreToolUse"
# Check user-level settings
cat ~/.claude/settings.json 2>/dev/null | grep -A5 "PreToolUse"
If no git-blocking hook exists, recommend adding one. Show the user what to add to .claude/settings.json:
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "python3 -c \"import sys,json; d=json.loads(sys.stdin.read()); cmd=d.get('tool_input',{}).get('command',''); git_cmds=['git commit','git add','git checkout','git branch','git stash','git merge','git rebase','git push','git pull','git reset','git cherry-pick']; matches=[c for c in git_cmds if c in cmd]; sys.exit(0) if not matches else (print(json.dumps({'decision':'block','reason':f'Use jj instead of {matches[0]}. This repo is managed by jj — raw git commands can corrupt state.'})), sys.exit(0))\"",
"timeout": 5
}
]
}
]
}
}
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.
- 3d ago First seen · 137 lines · 19 tokens per session scan A f9b9d8b72c23
tommymorgan:jj-setup is a command published in the GitHub repository tommymorgan/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 1,070 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.