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 paulinevos/claude-stuff --skill undo-opgit clone --depth 1 https://github.com/paulinevos/claude-stuffWrote 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/paulinevos/claude-stuff/undo-op)<a href="https://agentmods.dev/skills/paulinevos/claude-stuff/undo-op"><img src="https://agentmods.dev/badge/skills/paulinevos/claude-stuff/undo-op.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 22 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00095 | $0.00485 |
| Opus 5 | $0.00048 | $0.00243 |
| Sonnet 5 | $0.00019 | $0.00097 |
| Haiku 4.5 | $0.00010 | $0.00049 |
Grade A, and why
undo-op 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 8d 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.
What it actually says
undo-op
Almost every history-changing operation is reversible because git records where each ref pointed before it moved, in the reflog. Undoing means finding the entry just before the operation and moving the branch back to it.
Steps
- Inspect recent moves:
git reflog(orgit reflog show [branch]). Each line shows aHEAD@{N}position and the operation that produced it (rebase,commit --amend,reset,merge, …). - Identify the entry that describes the operation the user wants to undo, then
look one entry older — that's the state to return to. Confirm by inspecting
it:
git log --oneline HEAD@{N}and/orgit show HEAD@{N}. - Show the user that state and confirm it's the outcome they expect before changing anything — the next step is destructive to the current tip.
- Restore:
git reset --hard HEAD@{N}(run on the affected branch). The branch now points where it did before the operation.
Why the reflog, not git revert
git revert adds a new commit that inverts a change — appropriate for undoing a
published commit. Here the goal is to rewind local history as if the operation
never happened, which reset --hard to a reflog position does cleanly. Because
reflog entries persist for a while, even a "lost" commit after a bad rebase is
usually still recoverable this way.
Caution: reset --hard discards uncommitted changes. If there are any, stash
them first with git stash (-u to include untracked files), then
git stash pop after the reset.
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.
- 8d ago First seen · 36 lines · 95 tokens per session scan A 661cc6c20e08
undo-op is a skill published in the GitHub repository paulinevos/claude-stuff (64 stars, last pushed 26d ago), licensed MIT. It adds 95 tokens to every session and 485 once invoked, about $0.0005 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 2026-08-30.
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.
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…
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".