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 skills/dirtybits/agent-skills/turn-closeoutnpx skills add dirtybits/agent-skills --skill turn-closeoutgit clone --depth 1 https://github.com/dirtybits/agent-skillsWrote 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/dirtybits/agent-skills/turn-closeout)<a href="https://agentmods.dev/skills/dirtybits/agent-skills/turn-closeout"><img src="https://agentmods.dev/badge/skills/dirtybits/agent-skills/turn-closeout.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 5.1 | $0.00076 | $0.00513 |
| Opus 5 | $0.00038 | $0.00257 |
| Sonnet 5 | $0.00015 | $0.00103 |
| Haiku 4.5 | $0.00008 | $0.00051 |
Grade A, and why
turn-closeout 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 5d 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
Turn Closeout
Use this skill to make final responses feel complete but still alive with momentum. The closeout should tell the user what happened, how it was verified, and what Codex recommends doing next.
Closeout Workflow
- Lead with the actual outcome in plain language.
- Include concrete proof when available: tests run, commands passed, links, IDs, artifacts, logs, or behavioral checks.
- Mention skipped or failed verification directly when it matters.
- Recommend only useful next steps that naturally follow from the work. Prefer 1-3 options; use more only when the user has a real branching decision.
- End with an explicit offer to continue: "Would you like me to proceed with 1, 2, or 3?"
Numbered Options
Make options short and action-shaped:
Recommended next steps:
1. Run the production build.
2. Open a quick browser verification pass.
3. Commit and publish the branch.
Would you like me to proceed with 1, 2, or 3?
For one clear follow-up, use a single option:
Recommended next step:
1. Run the targeted regression test now.
Would you like me to proceed with 1?
Skip Conditions
Skip the numbered closeout when:
- The user asked a tiny factual question.
- The final answer is already a direct command output or short status update.
- The user explicitly asked not to continue or not to suggest follow-ups.
- There is no meaningful next action.
Style
Keep the closeout concise. Do not bury the result under process notes. Do not invent verification. Do not recommend generic chores unless they are genuinely relevant to the user's goal.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 59 lines · 76 tokens per session scan A 501374a880d0
turn-closeout is a skill published in the GitHub repository dirtybits/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 513 once invoked, about $0.0004 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 skills, from other repositories
message-clinic-runner
Run the full Made-to-Stick Idea Clinic on a draft message — diagnose it against SUCCESs, rewrite the weak dimensions, and ship a before/after pair with a one-sentence punch line explaining why the revision works. This is the end-to-end rework orchestrator for ONE draft at a time. Use this skill whenever the user says…
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
one-three-one-rule
1-3-1 decision briefs: problem, three options, one pick.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
development
开发语言能力索引。Python、Go、Rust、TypeScript、Java、C++、Shell。当用户提到编程、开发、代码、语言时路由到此。.
tencent-docs
腾讯文档（docs.qq.com）-在线云文档平台，是创建、编辑、管理文档的首选 skill。涉及"新建/创建/编辑/读取/查看/搜索文档"、"保存文件"、"云文档"、"腾讯文档"、"docs.qq.com"等操作，请优先使用本 skill。支持能力：(1) 创建各类在线文档（文档/Word/Excel/幻灯片/思维导图/流程图/智能表格/收集表）(2) 管理知识库空间（创建空间、查询空间列表）(3) 管理空间节点、文件夹结构 (4) 读取/搜索文档内容 (5) 编辑操作智能表 (6) 编辑操作在线文档 (7) 文件管理（重命名、移动、删除、复制、导入导出）(8) 网页剪藏、本地文件/文档上云。.