Berd is an open-source desktop application for working with AI agents through a graphical interface. It is intended for people who want to use different AI models and an integrated Goose backend from a desktop app. The catalogue entries add agent skills, agents, and instructions for working within Berd.
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 block/berd --skill berd-monitorgit clone --depth 1 https://github.com/block/berdWrote 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/berd/berd-monitor)<a href="https://agentmods.dev/skills/block/berd/berd-monitor"><img src="https://agentmods.dev/badge/skills/block/berd/berd-monitor/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/block/berd/berd-monitor"><img src="https://agentmods.dev/badge/skills/block/berd/berd-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.00417 |
| Opus 5 | $0.00021 | $0.00209 |
| Sonnet 5 | $0.00008 | $0.00083 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
berd-monitor 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 11d 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
Berd Monitor
Use berd-monitor when a command may outlive the current turn. It detaches the
producer from Berd and the agent harness, buffers output across delivery
failures, and sends complete stdout lines to the exact originating session.
Run short, bounded commands normally. Do not hold a turn open with sleep,
polling, log tailing, or a foreground timeout.
Start
berd-monitor run \
--state-key <stable-key> \
--label '<concise source name>' \
--instructions '<short event-handling guidance>' \
-- <producer-command> [args...]
AGENT_SESSION_ID selects the current session. Use --session-id only for
another positively identified session; never infer a session from the working
directory. The command prints the detached monitor PID. After checking the
monitor's watcher.log under the printed state directory when diagnosis is
needed, continue other work or end the turn—never wait on the detached PID.
The producer's stdout is the event API:
- emit concise, newline-terminated milestones and flush promptly;
- put verbose output and diagnostics in durable logs or stderr;
- avoid NUL bytes and emit a final summary when practical.
Default --if-running steer adds an event to an active run or starts a new
turn. Use --if-running queue only when the active run must not be steered.
Pending events retry without being dropped, and a trailing partial line is
delivered when the producer exits.
Delivered messages are visibly labeled as coming from berd-monitor. Stop a
monitor with:
berd-monitor stop --state-key <stable-key>
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.
- 11d ago First seen · 53 lines · 42 tokens per session scan A bfce94a9ac11
berd-monitor is a skill published in the GitHub repository block/berd (897 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 417 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
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…
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.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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.