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-loopgit 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-loop)<a href="https://agentmods.dev/skills/akougkas/zulipchat-mcp/zulipchat-loop"><img src="https://agentmods.dev/badge/skills/akougkas/zulipchat-mcp/zulipchat-loop/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-loop"><img src="https://agentmods.dev/badge/skills/akougkas/zulipchat-mcp/zulipchat-loop.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 | $0.00026 | $0.00261 |
| Opus 5.5 | $0.00010 | $0.00104 |
| Sonnet 5.5 | $0.00005 | $0.00052 |
| Haiku 4.5 | $0.00003 | $0.00026 |
Grade A, and why
zulipchat-loop 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 15d 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.
What it actually says
Use this workflow only for the continuing task the user authorized. Retain the
current session binding, objective, constraints, event cursor, and outstanding
request IDs. Between substantial work cycles, poll poll_agent_events, process
verified owner commands, then continue useful task work and post meaningful
milestones through agent_message.
Stop when the task is complete or canceled. Pause only at the owner's request. When input is required, persist the concrete request and wait without treating elapsed time as a decision. A host-native scheduling or loop facility may drive the cycles; this skill does not install one or grant additional permissions.
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.
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.
- 15d ago Changed · -13 lines · +6 tokens per session 93f43777b356
- 1mo ago First seen · 37 lines · 20 tokens per session scan A 656a74c32b66
zulipchat-loop is a skill published in the GitHub repository akougkas/zulipchat-mcp (33 stars, last pushed 16d ago), licensed MIT. It adds 26 tokens to every session and 261 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.
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…
package-remove
Uninstall a UPM package from the Unity project. Modifies manifest.json and may trigger a domain reload — the final result is delivered after the reload via the request's requestId. Built-in packages and packages that are dependencies of others cannot be removed. Use 'package-list' to list installed packages first.
screenshot-game-view
Capture a screenshot of the Unity Editor's Game View by reading its internal render texture directly. Image size matches the current Game View resolution; the tool corrects Y-flip on DirectX / Metal so the output is always upright. Requires an open Game View window.
editor-session-quit
Save and quit an editor that a CLI session started (unity-mcp-cli exec, open --headless). Needs the session lease nonce; an editor the user opened is never closed. Used by unity-mcp-cli close.
agent-teams
Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.
Launch Communications Generator
Draft launch communications: an announcement / press release, an internal support FAQ, and a customer-facing feature summary. Use for launch comms, press release, announcement, and messaging.