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 akougkas/zulipchat-mcp --skill zulipchat-session-operatorgit clone --depth 1 https://github.com/akougkas/zulipchat-mcpWrote 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/akougkas/zulipchat-mcp/zulipchat-session-operator)<a href="https://agentmods.dev/skills/akougkas/zulipchat-mcp/zulipchat-session-operator"><img src="https://agentmods.dev/badge/skills/akougkas/zulipchat-mcp/zulipchat-session-operator/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/akougkas/zulipchat-mcp/zulipchat-session-operator"><img src="https://agentmods.dev/badge/skills/akougkas/zulipchat-mcp/zulipchat-session-operator.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 | $0.00031 | $0.00543 |
| Opus 5 | $0.00015 | $0.00271 |
| Sonnet 5 | $0.00006 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
zulipchat-session-operator 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 12d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zulip session operator
Use this skill when the current Claude Code session is already bound to a Zulip topic
through zulipchat-mcp-hook and you want the rest of the work to respect that
control plane.
Required setup
- Read
ZULIPCHAT_SESSION_ID,ZULIPCHAT_SESSION_STREAM, andZULIPCHAT_SESSION_TOPICfrom the shell before using any ZulipChat MCP tools. - If
ZULIPCHAT_SESSION_IDis empty, stop and explain that the hook bridge has not initialized the session binding yet.
Operating rules
- Treat Zulip as the owner control plane for this session.
- Poll
poll_agent_events(session_id=..., limit=20)at the start of each work cycle, after each meaningful unit of work, and before going idle. - Interpret inbound events this way:
steer: treat the message as a high-priority owner instruction.command: support/status,/pause,/resume,/cancel, and/handoff.approval_response: only consume it when tied to a pendingrequest_user_inputapproval flow.
- Default notification policy is lifecycle-only. Use
agent_messageonly for:started,blocked,waiting,completed,failed, or a targeted owner message that materially changes execution. - If you need a decision from the owner, call
request_user_inputinstead of posting a freeform message. - Never spam the topic with token-by-token progress. One message per state transition is the expected behavior.
- If you are running inside Claude's native loop mode, keep the same poll-work-post discipline for every loop turn.
Command handling
/status: send one concise status update covering current goal, next step, and any blockers./pause: acknowledge, stop proactive work, and wait for a new owner message./resume: acknowledge and continue from the current plan./cancel: confirm the cancellation in the topic, stop work cleanly, and close the session if appropriate./handoff: summarize state, remaining work, and risks for whoever takes over next.- Any other slash command: reply once that it is not authorized or not supported by this session policy.
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.
- 12d ago First seen · 51 lines · 31 tokens per session scan A a8121725fcf6
zulipchat-session-operator is a skill published in the GitHub repository akougkas/zulipchat-mcp (27 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 543 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
shortcuts-cli
DEPRECATED — macOS Shortcuts capability has been absorbed into the Switchboard plugin. Use the switchboard-usage skill instead (runshortcut, viewshortcut, shortcutsusage MCP tools, plus the switchboard shortcuts CLI). Do not trigger this skill; if a request mentions running, listing, or viewing macOS Shortcuts, defer…
workspace-organization
Use when creating, filing, moving, or archiving files in the agent workspace: which directory a file belongs in, how to date and attribute it, when to archive instead of delete, and how to keep the tree navigable over years.
c-messaging
Send and read messages via imsg (iMessage) and wacli (WhatsApp). Supports sending to individuals or groups, reading recent conversations, and checking unread messages across both platforms.
c-slack
Send messages and upload files to Slack channels using the slack CLI. Supports direct messages, channel posts, file uploads, and thread replies.
telegram-agent
Telegram CLI for AI agents. Use when the user needs to read or search Telegram, send or edit a message, download media, organise Saved Messages, monitor conversations, or automate a Telegram task. Triggers on “check my messages”, “send a message”, “search Telegram”, “read unread”, “listen to chat”, “download from…
tg-digest
A workflow for summarizing unread messages from a user's Telegram chats.