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/fusengine/agents/undogit clone --depth 1 https://github.com/fusengine/agentsWrote 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/fusengine/agents/undo)<a href="https://agentmods.dev/commands/fusengine/agents/undo"><img src="https://agentmods.dev/badge/commands/fusengine/agents/undo.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 | $0.00018 | $0.00318 |
| Opus 5 | $0.00009 | $0.00159 |
| Sonnet 5 | $0.00004 | $0.00064 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
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
Undo Last Commit
Current State
!git status
Last Commit
!git log -1 --pretty=format:'%h %s'
Remote Status
!git log origin/HEAD..HEAD --oneline 2>/dev/null || echo "No remote tracking"
Instructions
Safely undo the last commit while keeping changes.
Security Check (MANDATORY)
IF the last commit is already pushed to remote:
- REFUSE to reset
- Explain: "Cannot undo pushed commits with reset."
- Suggest:
git revert HEADto create a reverting commit - Ask confirmation before executing revert
IF the last commit is NOT pushed:
- Ask confirmation: "Undo last commit? Changes will be kept."
- Determine mode:
--soft(default): Keep changes staged--mixed: Keep changes unstaged
- Execute:
git reset $ARGUMENTS HEAD~1 - Show result with
git status
Options
| Flag | Effect |
|---|---|
--soft |
Keep changes staged (default) |
--mixed |
Keep changes unstaged |
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 · 48 lines · 18 tokens per session scan A a0a8bd11dbf5
undo is a command published in the GitHub repository fusengine/agents (25 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 318 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 2026-09-03.
Other commands, from other repositories
commit-claude-config
Version the Solana AI Kit config in git (un-ignores .claude/, CLAUDE.md, .mcp.json, .gitmodules and commits them).
commit
Analyze git diffs or staged changes and generate conventional commit messages that explain WHY a change was made. Supports auto-detecting type and scope, intelligent file staging, and interactive overrides. Use when asked to "write a commit message", "generate a commit", "describe my changes", "commit this"…
nyann:commit
Generate a Conventional Commits message from the staged diff and commit after confirmation. Same flow as the natural-language commit skill — dispatches here so users who prefer explicit slash commands can bypass intent detection.
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.