berd-monitor

berd-monitor is a skill for Claude Code, Codex from block/berd. It costs 42 tokens per session (417 once invoked), scanned A, original, Apache-2.0.

A monitor for commands that continue after the current coding-agent turn ends. It records their output and sends useful progress or completion messages back to the session that started them.

In plain words
What is it for?
Use it for long-running builds, test suites, code reviews, deployments, polling tasks, file watchers, and other commands that may outlive the current turn.
Why use it?
Long builds, tests, deployments, and watchers can otherwise block the agent or lose their output. This keeps the work running while the agent moves on.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one.

Good fit Use it for long-running builds, test suites, code reviews, deployments, polling tasks, file watchers, and other commands that may outlive the current turn.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/block/berd/berd-monitor
View source ↗ block/berd
About the project

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.

block/berd · 897 stars · on GitHub

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 block/berd --skill berd-monitor
Clone the repo
git clone --depth 1 https://github.com/block/berd

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 berd-monitor

README.md
[![agentmods](https://agentmods.dev/badge/skills/block/berd/berd-monitor/github.svg)](https://agentmods.dev/skills/block/berd/berd-monitor)
Your own site
<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.

agentmods 80×15 button for berd-monitor

Your own site · 80×15
<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>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 417 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00042 $0.00417
Opus 5 $0.00021 $0.00209
Sonnet 5 $0.00008 $0.00083
Haiku 4.5 $0.00004 $0.00042

Measured 11d ago against content hash bfce94a9ac11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

distro/skills/berd-monitor/SKILL.md · 53 lines

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>
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. 11d ago First seen · 53 lines · 42 tokens per session scan A bfce94a9ac11

Subscribe to this mod's changes

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.