zulipchat-session-operator

zulipchat-session-operator is a skill for Claude Code, Codex from akougkas/zulipchat-mcp. It costs 33 tokens per session (414 once invoked), scanned A, original, MIT.

A set of instructions for running a Claude Code session under control of a Zulip topic. Zulip is a team chat system, and the topic can provide steering, approvals, commands, and session updates.

In plain words
What is it for?
Use it when a session has been connected to Zulip by the session hook and must follow messages from its assigned Zulip topic.
Why use it?
It defines how the session should receive owner instructions and handle pause, resume, cancellation, handoff, and approval requests.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it when a session has been connected to Zulip by the session hook and must follow messages from its assigned Zulip topic.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/akougkas/zulipchat-mcp/zulipchat-session-operator
Install

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.

Any agent
npx skills add akougkas/zulipchat-mcp --skill zulipchat-session-operator
Clone the repo
git clone --depth 1 https://github.com/akougkas/zulipchat-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for zulipchat-session-operator

README.md
[![agentmods](https://agentmods.dev/badge/skills/akougkas/zulipchat-mcp/zulipchat-session-operator/github.svg)](https://agentmods.dev/skills/akougkas/zulipchat-mcp/zulipchat-session-operator)
Your own site
<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.

agentmods 80×15 button for zulipchat-session-operator

Your own site · 80×15
<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>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 414 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.00414
Opus 5.5 $0.00013 $0.00166
Sonnet 5.5 $0.00007 $0.00083
Haiku 4.5 $0.00003 $0.00041

Measured 21d ago against content hash 797612718d4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 21d 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.

integrations/antigravity-cli/.agents/skills/zulipchat-session-operator/SKILL.md · 33 lines

What it actually says

Use the bound agent_id and session_id from the host context or from register_agent and ensure_agent_session. Claude hooks may expose these as ZULIPCHAT_AGENT_ID and ZULIPCHAT_SESSION_ID; other hosts can retain tool results. Never infer ownership from message text or a request ID alone.

Use agent_message for useful milestone, blocked, failure, completion, and handoff updates. Poll poll_agent_events between substantial steps when the extended tool is exposed. Preserve the event cursor to avoid repeating commands. Honor /status, /pause, /resume, /cancel, and /handoff from the verified owner. A canceled task stops; a resumed task retains its original objective. MCP delivers these control events; the coding host must apply them. It does not launch an agent or interrupt running local tools. Report a pause or cancellation as requested until the host confirms that transition; do not claim enforcement from event receipt alone.

For approval, persist a concrete request with request_user_input, retain its ID, and use wait_for_response for that request. Only an immutable decision for the matching request and owner/session is actionable. A wait timeout is not an approval. Keep the coding host's existing permission checks in effect.

For owner questions, advertise /reply REQUEST_ID YOUR ANSWER. For approval requests use /approve REQUEST_ID or /deny REQUEST_ID. Poll with wait_for_response(request_id=..., timeout_seconds=30) and retain the same request ID after a timeout. Resume polling instead of posting a duplicate prompt. For replayable steering, use poll_agent_events(auto_ack=False, session_id=...) and acknowledge consumed event IDs on the next poll with ack_event_ids.

Changes

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.

  1. 21d ago Changed · -18 lines · +2 tokens per session 797612718d4a
  2. 2mo ago First seen · 51 lines · 31 tokens per session scan A a8121725fcf6

Subscribe to this mod's changes

zulipchat-session-operator is a skill published in the GitHub repository akougkas/zulipchat-mcp (33 stars, last pushed 21d ago), licensed MIT. It adds 33 tokens to every session and 414 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

Other skills, from other repositories