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 okolovmark/nixodoo-copier-template --skill if-status_mcp-teams-teams-message-endifgit clone --depth 1 https://github.com/okolovmark/nixodoo-copier-templateWrote 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/okolovmark/nixodoo-copier-template/if-status_mcp-teams-teams-message-endif)<a href="https://agentmods.dev/skills/okolovmark/nixodoo-copier-template/if-status_mcp-teams-teams-message-endif"><img src="https://agentmods.dev/badge/skills/okolovmark/nixodoo-copier-template/if-status_mcp-teams-teams-message-endif/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/okolovmark/nixodoo-copier-template/if-status_mcp-teams-teams-message-endif"><img src="https://agentmods.dev/badge/skills/okolovmark/nixodoo-copier-template/if-status_mcp-teams-teams-message-endif.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 | $0.00082 | $0.02118 |
| Opus 5 | $0.00041 | $0.01059 |
| Sonnet 5 | $0.00016 | $0.00424 |
| Haiku 4.5 | $0.00008 | $0.00212 |
Grade A, and why
teams-message 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 4d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teams message
One message, readable at chat width (~90 chars), written as the user. Also the
formatting authority for every other skill that posts to Teams (my-status,
deploy/pipeline notifications): those own what is sent, this owns how it is
shaped and sent.
Transport is the claude.ai Microsoft 365 connector
(mcp__claude_ai_Microsoft_365__teams_*), which the user connects in their
claude.ai under Customize → Connectors. There is no project-level Teams
MCP server to install.
Hard rules
- Write HTML and pass
bodyType: "html". The connector does no markdown pass at all — it takes text or HTML and sanitizes the HTML. Markdown syntax posted as a body lands literally:**Modules:**renders as asterisks,- itemas a hyphen,[label](url)as brackets. This is the single most common way a message comes out unreadable.bodyType: "text"(the default) is for a genuinely one-paragraph message and nothing else. - A sent message cannot be edited or deleted. The connector exposes no update or delete tool. There is no read-back-and-fix loop any more: the draft gate below is the only correction opportunity. Re-read the recipient and the body before sending.
- English body, always — whatever language the session runs in. The draft shown to the user is English too.
- DM recipient resolved fresh:
search_peopleby name, match the email in the result, and only then take/create the chat. Never reuse a chat id carried in context — the id encodes an opaque GUID, so a wrong recipient is invisible in the call and in the success response. Watch for duplicate same-name accounts (old/disabled mailboxes); pick the live one. Fixed group chat ids from the identity memory node are exempt. - It is the user speaking, not an assistant. No offers of extra work ("want me to check X", "let me know if you want a hand") — the message is signed by a person with their own backlog. End on the fact, or on the step the recipient takes.
- No AI style tells: no em dashes, no contractions (write "do not", "it is", "I have"), no "not just X, but Y", no triadic parallel lists, no buzzwords (delve, leverage, seamless, robust, empower, unlock), no emoji bullets, no "I am excited to" / "Let's connect".
- Draft first, send on the go. Show the exact text and wait. A request that already dictates the content ("send him: ...") is itself the go.
- One message per go. Never split into a burst of follow-ups.
- Body cap is 27000 bytes, and sends are rate-limited per user; a batch of messages needs pacing and a retry after a short delay.
What ships with it
1 file 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.
- 4d ago Changed · +23 lines 5759523f936b
- 12d ago First seen · 118 lines · 82 tokens per session scan A 00996761cffb
teams-message is a skill published in the GitHub repository okolovmark/nixodoo-copier-template (5 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 2,118 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.