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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/block/buzznpx agentmods add skills/block/buzz/screenshotWrote 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/screenshot)<a href="https://agentmods.dev/skills/block/buzz/screenshot"><img src="https://agentmods.dev/badge/skills/block/buzz/screenshot.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 | $0.00020 | $0.00947 |
| Opus 5 | $0.00010 | $0.00474 |
| Sonnet 5 | $0.00004 | $0.00189 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
desktop-screenshot 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 2d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Desktop Screenshot Skill
CRITICAL: How to Host Screenshots for PRs
NEVER use buzz upload, the relay media endpoint, or any third-party image
host (imgur, imgbb, etc.) for PR screenshots. Relay media URLs fail through
GitHub's camo proxy (Non-Image content-type returned). External hosts are
unreliable and may expose content.
ALWAYS use scripts/post-screenshots.sh — it hosts PNGs on a per-developer
git branch with immutable commit-SHA URLs that render correctly on GitHub.
If you manually compose or edit PR markdown, run
scripts/check-pr-image-urls.sh <markdown-file> before posting. The checker
fails on Buzz/relay media URLs so broken images are caught locally.
This hosting rule applies to any PNG you want in a PR, including mobile simulator screenshots captured outside the desktop Playwright helper.
Step 1 — Capture Screenshots
just desktop-screenshot builds the frontend, starts a preview server, and
runs Playwright with the mock bridge (no relay needed).
just desktop-screenshot --name home
just desktop-screenshot --name channel --route /channels/general
just desktop-screenshot --name ctx-menu --right-click channel-random --clip 0,200,320,300
just desktop-screenshot --name sidebar --active-channel general --messages /tmp/msgs.json --clip 0,0,256,720
Flags: --name (filename, required), --route (client route), --active-channel
(channel to view), --click/--right-click/--hover (interact before capture),
--clip (crop as x,y,w,h), --messages (JSON file), --wait (ms, default 2000),
--viewport (WxH, default 1280x720), --outdir (default test-results/screenshots).
Output: PNG path on stdout.
Injecting Messages
Write a JSON array to a temp file. channelName and content are required:
[
{"channelName": "random", "content": "Hey check this out", "kind": 40002},
{"channelName": "random", "content": "Another message"}
]
Without --active-channel, the helper navigates to the message channel (for
showing content). With --active-channel, messages can target other channels
while the camera stays put (for unread indicators, badges).
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.
- 2d ago First seen · 104 lines · 20 tokens per session scan A 8dc4bd6a0047
desktop-screenshot is a skill published in the GitHub repository block/buzz (32,211 stars, last pushed yesterday), licensed Apache-2.0. It adds 20 tokens to every session and 947 once invoked, about $0.0001 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
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.