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/musingfox/cc-plugins/jj-cleangit clone --depth 1 https://github.com/musingfox/cc-pluginsWhat 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 | $0.00016 | $0.00469 |
| Opus 5 | $0.00008 | $0.00234 |
| Sonnet 5 | $0.00003 | $0.00094 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
jj-clean 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 yesterday.
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.
What it actually says
jj-clean — Clean Up Empty Changes
Find and remove empty or obsolete changes to keep the repository tidy.
Environment Detection
if [ ! -d ".jj" ] && ! jj root 2>/dev/null; then
echo "NOT_JJ_REPO"
fi
If NOT a jj repo, inform the user and stop.
Workflow
Step 1: Find Candidates
Run these queries to find cleanup candidates:
Empty changes (owned by user):
jj log --revisions "empty() & mine() & ~heads(trunk())"
Changes with no description:
jj log --revisions "description(exact:'') & mine()"
Step 2: Present Candidates
Show the candidates grouped:
## Cleanup Candidates
### Empty Changes
[list of empty changes with IDs and parents]
### Undescribed Changes
[list of changes with no description]
**Total**: [N] candidates found
If no candidates found, inform the user the repo is clean and stop.
Step 3: Confirm with User
Use AskUserQuestion to ask:
- "Abandon all [N] empty changes?" with options:
- "Yes, abandon all" — abandon all candidates
- "Let me pick" — show each candidate individually for yes/no
- "No, cancel" — abort
Step 4: Execute Cleanup
For each confirmed change:
jj abandon <change-id>
Important: Never abandon the working copy (@) or changes that are ancestors of bookmarks pointing to remote-tracking branches.
Step 5: Report
## Cleanup Complete
**Abandoned**: [N] changes
**Skipped**: [N] changes (if any were skipped)
Safety Rules
- NEVER abandon changes that have bookmarks with remote tracking
- NEVER abandon the current working copy (
@) - NEVER abandon changes that are ancestors of non-empty changes
- If unsure about a change, skip it and report why
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.
- yesterday First seen · 89 lines · 16 tokens per session scan A 3372c95f22e9
jj-clean is a command published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 469 once invoked, about $0.0001 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 commands, from other repositories
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.