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/vertiso/memory-vscode/wrap-upnpx skills add Vertiso/memory-vscode --skill wrap-upgit clone --depth 1 https://github.com/Vertiso/memory-vscodeWhat 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 | $0.00073 | $0.03585 |
| Opus 5 | $0.00036 | $0.01792 |
| Sonnet 5 | $0.00015 | $0.00717 |
| Haiku 4.5 | $0.00007 | $0.00359 |
Grade A, and why
wrap-up 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 2d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wrap-up
Close out a finished session: close the completed work in Vertiso Memory — complete the actions that shipped, archive the intents and projects whose full scope is done — journal the stable state, and ensure every deferred follow-on is tracked — as a vmem ACTION (a concrete piece of work) or, for a measurable outcome to achieve or maintain, an intent.
Announce: "Using the wrap-up skill to close out this session."
Consent boundary
Invoking this skill at the user's request, or affirmatively accepting an agent's offer to run it, authorizes one capture. Invocation authorizes the wrap-up memory and its checkpoint-backed transcript gathering, including selected attributed verbatim excerpts sent to Vertiso Memory. Once invoked, do not ask a second permission question for that capture. It does not authorize creating, completing, or archiving actions, intents, or projects; those additional mutations retain the explicit confirmation step below.
Do not ask whether to write the wrap-up memory; the user's invocation already authorized it. When follow-on or closure candidates exist, ask only whether to create or close those named actions/intents/projects, and state that the wrap-up memory will be written regardless. If both lists are empty, proceed without another question.
One invocation does not grant standing authorization for later wrap-ups. Omit and do not persist passwords, API keys, authentication tokens, payment information, illegal or illicit materials, or sensitive third-party information the user is not authorized to store.
Secret stripping
Before composing the memory, inspect every selected source, including the conversation, transcript, work artifacts, tool output, title, tags, and metadata, for secrets. Treat passwords, API keys, bearer or refresh tokens, OAuth codes, session cookies, private keys, recovery codes, and credentialed connection strings as secrets.
Strip or redact any detected value before composing the memory. Never send the original value to Vertiso Memory or copy it into a quote, title, tag, metadata, link, or error detail. Do not echo the secret in the report; state only that sensitive content was omitted. If sanitization would make the capture meaningless, stop and ask the user for a sanitized replacement.
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.
- 2d ago First seen · 265 lines · 73 tokens per session scan A 7ae20a50800d
wrap-up is a skill published in the GitHub repository Vertiso/memory-vscode (0 stars, last pushed 5d ago), licensed MIT. It adds 73 tokens to every session and 3,585 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
lark-im
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
reflect
Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
organize-threads
猫猫辅助整理未分类 thread，分析标题和元数据，建议合适的标签。 Use when: 用户说"帮我整理"、"分类 thread"、点击整理按钮。 Not for: 删除/编辑标签本身。 Output: 按 thread 的标签建议列表。.