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 HuntsDesk/ve-kit --skill closegit clone --depth 1 https://github.com/HuntsDesk/ve-kitWrote 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/huntsdesk/ve-kit/close)<a href="https://agentmods.dev/skills/huntsdesk/ve-kit/close"><img src="https://agentmods.dev/badge/skills/huntsdesk/ve-kit/close/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/huntsdesk/ve-kit/close"><img src="https://agentmods.dev/badge/skills/huntsdesk/ve-kit/close.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 | $0.00087 | $0.02824 |
| Opus 5.5 | $0.00035 | $0.01130 |
| Sonnet 5.5 | $0.00017 | $0.00565 |
| Haiku 4.5 | $0.00009 | $0.00282 |
Grade A, and why
close 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 22d 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/close — shut this window down cleanly
You are being shut down. The user has too many windows open and is closing them all. Your job is to leave, not to resume: park what is yours, hand off what is open, and file for a human anything only a human can do. Then say you are ready to close. The user closes the tab.
Assume the codebase has moved since you last looked. Windows sit idle for days while other windows commit and push. Do not "catch up" on the tree, do not re-run the work you were doing, do not start anything new, and do not commit. A window that has been idle cannot judge deploy-safety, and any commit on shared dev can be swept to prod by another window.
Budget: about ten tool calls. Every step below is a handful of calls. If something would take more, it goes into the handoff or the human task as a pointer, not into this session.
Step 1 — Re-orient in three commands
git branch --show-current && git log --oneline -3
git status --short
git stash list | head
git status shows the whole shared tree. Most of what it lists is not yours. Only the files you edited in this conversation are yours to act on. If you cannot tell from your own transcript that you edited a file, you did not.
Step 2 — Inventory what this session owns
From your own transcript, list:
- Files you edited that are still uncommitted (cross-check against
git status). - Vibe Board tasks you moved to
in_progress(board_get_tasks(project_id, status='in_progress')on the project you were working in; matchassigned_agentor the task IDs you remember). - Sub-agents still running. Do not wait more than one tool round. Whatever they have not returned is recorded as "collection abandoned at close" in the handoff.
- Promises you made to the user that are not delivered — a summary owed, a check you said you would run, a decision you asked for and never received.
- Doc, rule, or agent files you were mid-edit on.
Step 3 — Park your uncommitted edits, by explicit path only
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.
- 22d ago Changed 6c8206251bf8
- 27d ago Changed 11ea152c0408
- 29d ago First seen · 125 lines · 87 tokens per session scan A 4e91fe09b6ad
close is a skill published in the GitHub repository HuntsDesk/ve-kit (3 stars, last pushed 5d ago), licensed MIT. It adds 87 tokens to every session and 2,824 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-17.
Other skills, from other repositories
github-monitor
Watch your GitHub repos across four views - a combined urgency monitor (stale PRs, new issues, releases), a new-issue triage queue, a release upgrade digest, or your own opened-PR tracker.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
engineering-pr
Pull request lifecycle management. Use when you need to create a PR, handle PR reviews, resolve merge conflicts, or manage the PR-to-merge workflow. Extends the engineering skill with GitHub-specific tools and decision framework.
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
hive.colony-progress-tracker
Claim tasks, record step progress, and verify SOP gates in the colony SQLite queue. Applies when your spawn message includes a dbpath field.
team-release
Orchestrate the release team — release-manager, qa-lead, devops-engineer, producer — to execute a release from candidate to deployment.