Buzz is a self-hostable workspace where people and AI agents share rooms, communicate through signed events, and collaborate on repositories, workflows, canvases, and code reviews. It is for teams that want humans and agents to work together on software through a relay they control. The catalogue entries are agents, skills, and instructions for using Buzz’s collaborative workflows.
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/block/buzz/nestnpx skills add block/buzz --skill nestgit clone --depth 1 https://github.com/block/buzzWrote 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/block/buzz/nest)<a href="https://agentmods.dev/skills/block/buzz/nest"><img src="https://agentmods.dev/badge/skills/block/buzz/nest.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 | $0.00041 | $0.02647 |
| Opus 5 | $0.00020 | $0.01324 |
| Sonnet 5 | $0.00008 | $0.00529 |
| Haiku 4.5 | $0.00004 | $0.00265 |
Grade A, and why
buzz-cli 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 yesterday.
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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buzz CLI Skill
Environment
BUZZ_PRIVATE_KEY is set by the harness at runtime or by the developer's environment. If missing, tell the user to set it (hex or nsec format). Never read or echo the value.
BUZZ_RELAY_URL defaults to http://localhost:3000. In development, the user may need to set this to a staging or production relay URL.
BUZZ_AUTH_TAG is required for buzz agents draft-create and buzz agents draft-update because those commands send owner-reviewed Desktop drafts. If missing, explain that this managed agent cannot open owner-reviewed agent drafts from chat.
Run the bundled CLI with --help and <command> <subcommand> --help to discover all flags, arguments, and usage. This skill documents only what --help cannot tell you.
Conversational Agent Management
When someone naturally asks to create an agent, ask for at most two things: the agent's name and what it should do day-to-day. Turn the user's rough purpose into the system prompt yourself; do not separately ask for purpose, tone, constraints, access, runtime, provider, or model unless the request is genuinely ambiguous. Then run:
buzz agents draft-create \
--channel <current-channel-uuid> \
--display-name "Research helper" \
--system-prompt "Find reliable sources and summarize them concisely."
Use the UUID from the current Buzz [Context]; do not ask the user for it. Do not ask about runtime, provider, model, credentials, environment variables, or access. Desktop uses the machine's real defaults, and new agents start as Only me. The command sends an encrypted draft to the owner's Desktop. It does not create the agent until the owner reviews and saves the form, so report the result as “ready for review,” never “created.”
For an explicit change to an existing personal agent, use:
buzz agents draft-update --channel <uuid> --agent-name "Current name" \
--system-prompt "Updated instructions"
Run buzz agents draft-update --help for optional runtime, provider, model, rename, and access changes. Prefer these CLI commands over any legacy MCP agent-management tools.
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.
- yesterday First seen · 176 lines · 41 tokens per session scan A 672b8b1918f7
buzz-cli is a skill published in the GitHub repository block/buzz (32,211 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 2,647 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 2026-09-05.
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…
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…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.