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 finish-slicesgit 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/finish-slices)<a href="https://agentmods.dev/skills/paulinevos/claude-stuff/finish-slices"><img src="https://agentmods.dev/badge/skills/paulinevos/claude-stuff/finish-slices/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/paulinevos/claude-stuff/finish-slices"><img src="https://agentmods.dev/badge/skills/paulinevos/claude-stuff/finish-slices.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00034 | $0.00392 |
| Opus 5.5 | $0.00014 | $0.00157 |
| Sonnet 5.5 | $0.00007 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade C, and why
finish-slices scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 21d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "${HOME}/.jj-workspaces/<repo>/<slice>" What it actually says
finish-slices
Run from the default workspace. For every slice, verify its revisions are described, conflict-free, and all reachable from its bookmark:
jj log -r '<base>..<slice>' --no-graph --reversed -T 'change_id.short() ++ " " ++ description.first_line() ++ "\n"'
jj log -r '(<base>..<slice>) & (conflicts() | description(exact:""))'
jj log -r '(<slice>:: ~ <slice>) ~ working_copies() ~ ::(bookmarks() ~ <slice>)'
If needed, fetch and rebase the slice onto trunk() (or its child onto its
parent), then verify again. Fix an unadvanced bookmark only when its worker has
finished and the repair is mechanical.
Show the per-slice revision lists and parent-first push order; wait for explicit
approval before jj git push --bookmark <slice>. Stack child PRs on their
parent. When a parent merges, rebase and push its child, then retarget it to
main.
Keep a workspace while its PR may need changes. Once that PR merges:
jj git fetch
jj bookmark delete <slice> # or `jj bookmark forget` if the forge removed it
jj workspace forget <slice>
rm -rf "${HOME}/.jj-workspaces/<repo>/<slice>"
jj workspace list
Forget by name from the default workspace, never from the workspace being
forgotten. jj forget removes only jj's record; always remove the directory.
An empty @ is abandoned automatically; reconcile or abandon a non-empty
anonymous head before cleanup.
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.
- 21d ago Changed · -38 lines · -108 tokens per session 2113769cf1f5
- 1mo ago First seen · 78 lines · 142 tokens per session scan C b49c465b257e
finish-slices is a skill published in the GitHub repository paulinevos/claude-stuff (64 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 392 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-10.
Other skills, from other repositories
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
changelog
Auto-generate a changelog from git commits and sprint data. Internal and player-facing versions.
comet-safe-delivery
A Chinese-language procedure for safely delivering specified Comet changes through Git. It covers checking worktrees and unrelated edits, staging exact files, validating hooks, and authorized commits or pushes.
git-workflow
Guided git workflows: prepare PRs, clean up branches, resolve merge conflicts, handle monorepo tags, squash-and-merge patterns. Use when asked to prepare a PR, clean branches, resolve conflicts, or tag a release.
git-push
A GitHub publishing workflow that handles first-time uploads, routine updates, and tagged releases. Git is a system for recording code changes, while GitHub hosts repositories and releases online.
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.