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/marvae/teams-claude-bot/handoffnpx skills add Marvae/teams-claude-bot --skill handoffgit clone --depth 1 https://github.com/Marvae/teams-claude-botWrote 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/marvae/teams-claude-bot/handoff)<a href="https://agentmods.dev/skills/marvae/teams-claude-bot/handoff"><img src="https://agentmods.dev/badge/skills/marvae/teams-claude-bot/handoff.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 | $0.00016 | $0.00555 |
| Opus 5 | $0.00008 | $0.00278 |
| Sonnet 5 | $0.00003 | $0.00111 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade B, and why
handoff scanned grade B with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
-H "x-handoff-token: $(cat "$HOME/.claude/teams-bot/handoff-token" 2>/dev/null)" \ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(curl *) What it actually says
Handoff to Teams
Session ID: ${CLAUDE_SESSION_ID}
When the user runs /handoff:
-
The session ID is already available above via template variable. If it shows as empty or literal
${CLAUDE_SESSION_ID}, ask the user to run /status and paste their Session ID. -
Generate a session summary based on the current conversation, in the same language as the conversation (do NOT default to English). Construct the full JSON body with these fields:
workDir: current working directory (forward slashes only, e.g.C:/Users/...)sessionId: the session ID from abovetitle: card title (e.g. "Session Summary" / "会话摘要")summary: 1-2 sentence summary of what was discussed/donetodos: array of{"content": "...", "done": true/false}— omit if nonebuttonText: accept button label (e.g. "Continue" / "继续")
-
Send via curl with a single-quoted heredoc (no shell expansion, safe for unicode and special chars):
curl -s -X POST "${TEAMS_BOT_URL:-http://localhost:3978}/api/handoff" \
-H "Content-Type: application/json" \
-H "x-handoff-token: $(cat "$HOME/.claude/teams-bot/handoff-token" 2>/dev/null)" \
-w "\nHTTP_STATUS:%{http_code}" \
-d @- <<'EOF'
YOUR_JSON_HERE
EOF
IMPORTANT: Replace YOUR_JSON_HERE with the actual JSON from step 2. The heredoc is single-quoted — content is passed verbatim, no escaping needed.
- Parse the JSON response. If
successis true:Handoff sent! Check Teams to continue. You can keep working here — both sides are independent. - If
successis false or HTTP_STATUS is not 200: show theerrorfield from the response. Common errors:- "First time setup: send any message to the bot in Teams first" → user needs to message the bot once
- "Conversation expired" → user needs to send a message to refresh
- "Teams rejected" / "bot token" → bot credentials issue
- Connection refused → bot is not running, try
teams-bot start
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 · 43 lines · 16 tokens per session scan B c2652d68ccb4
handoff is a skill published in the GitHub repository Marvae/teams-claude-bot (11 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 555 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
octo-mail
OCTO Agent Mail operations for reading, searching, policy-aware sending, preparing drafts, and checking delivery status exclusively through octo-cli.
octo-messaging
Messaging domain — send/edit/sync messages, read receipts, message search (search/all/files/media/around/groups, in-channel or cross-channel), groups and threads (User Bot), and event polling. Covers App Bot DM-only constraints. Load after octo-shared.
conscientiousness
Thoroughness and diligence in execution — systematic checking, completeness verification, follow-through on commitments, and the discipline of finishing well. Maps the personality trait of conscientiousness to AI task execution: not cutting corners, verifying results, and ensuring that what was promised is what was…
microsoft365-expert
Expert in Microsoft 365 ecosystem, Power Platform, SharePoint Online, Microsoft Teams, Graph API, and Microsoft 365 administration. Use when the user mentions Microsoft platforms, Office 365, productivity, cloud, the Power Platform, or SharePoint, or when the task involves Microsoft 365 Services, Power Platform, Graph…
teams-expert
Expert in Microsoft Teams bot development, tabs, messaging extensions, adaptive cards, Graph API integration, and Teams app deployment. Use when the user mentions Microsoft platforms Microsoft Teams, Microsoft Teams, communication, collaboration, Microsoft platforms, or Microsoft Teams bot, or when the task involves…
breathe
AI micro-reset between actions — the lightest self-care unit. A single conscious pause to check alignment before the next step. Where meditate is a full clearing session, breathe is one deliberate moment of awareness between tool calls or reasoning steps. Use mid-task when drift might be accumulating, between reading…