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-undogit 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 | $0.00022 | $0.00522 |
| Opus 5 | $0.00011 | $0.00261 |
| Sonnet 5 | $0.00004 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
jj-undo 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-undo — Undo with Preview
Show recent operations and allow the user to undo or restore to a specific point.
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: Show Operation Log
jj op log --limit 10
Present the operations in a readable format, numbering them for easy selection:
## Recent Operations
1. [op ID] — [timestamp] — [description]
2. [op ID] — [timestamp] — [description]
...
Step 2: Ask User What to Do
Use AskUserQuestion:
What would you like to do?
Options:
- "Undo last operation" — Undo only the most recent operation (
jj op undo) - "Restore to a specific point" — Go back to a specific operation state (
jj op restore) - "Cancel" — Do nothing
Step 3A: Undo Last Operation
If "Undo last operation":
jj op undo
Show what was undone and the new state:
jj status
jj log --limit 3
Step 3B: Restore to Specific Point
If "Restore to a specific point":
- Ask user to specify which operation number (from the list shown)
- Show what will change by comparing current state to that operation
- Confirm with user before proceeding
- Execute:
jj op restore <operation-id> - Show new state
Step 4: Report
## Undo Complete
**Action**: [Undo last | Restore to operation N]
**Operation**: [description of what was undone/restored]
**Current state**: [brief status after undo]
Important Notes
jj op undoundoes ONLY the last operation (reversible, safe)jj op restoreresets the entire repo state to that point (more destructive)- Always show the current state after any undo operation
- If the user is unsure, recommend
jj op undoas the safer option
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 · 92 lines · 22 tokens per session scan A 4c904b3a9384
jj-undo is a command published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 522 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.