Skip to content
Agentmart
Submit a tool

dnd

Hold incoming agent mail during a quiet window, then deliver one digest.

Skill by bllshttng

IndexedApache-2.0★ 2
Write a review

Chalk Labs

Need help deploying dnd?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/bllshttng-dnd

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Hold incoming agent mail during a quiet window, then deliver one digest.

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/dnd

What's inside

Skill name
dnd
Description
Hold incoming agent mail during a quiet window, then deliver one digest.
License
Apache-2.0
Metadata
internal: false
Instructions
38 lines in SKILL.md · view on GitHub

Files (2)

  • LIMITATIONS.md
  • SKILL.md

SKILL.md (first lines)

# DND

Do-not-disturb for this session. Mail addressed to this session never pastes into the prompt line. It queues durable, and the sender gets a receipt saying so. When the hold lifts, the held mail is delivered as one digest, with no new prompt needed. Your own typing is never muted.

## Route

| The user says | You run |
|---|---|
| A duration: "20", "for 20 minutes", "I need your time for 20 minutes" | `fno agents mail admin hold --for <N>` |
| A range: "10-15 minutes" | `fno agents mail admin hold --for 15` (the upper bound, so the hold cannot lift inside the window) |
| No duration | `fno agents mail admin hold --for 20` |
| "Until I go idle", with a duration | `fno agents mail admin hold --minutes <N>` |
| "Off", "cancel", "stop", "release", "done", "allow mail" | `fno agents mail admin hold --off` |
| "Is DND on?" | `fno agents mail admin hold --status` |

"Until I go idle" arms the idle clock, not the wall clock. Say in the report that this clock restarts on every prompt and ends at twice the window. Every other route arms the wall clock: a fixed deadline that never moves.

A real message (not a slash command, a `!` line, or a raw send) starts the conversation hold by itself. It lasts while the session answers plus the configured grace (2 minutes by default) and restarts with each message. `Off` or `cancel` ends it now. A DND you set with a duration keeps its full length. The conversation rules never shorten or replace it.

While a hold is live: `control:` mail and the session's own sends pass, so you can always reach yourself. When the hold ends, a `--raw` send parked at the gate runs once through the raw door. Mail never lands while you are typing in the pane. It also waits out a question the session is asking. When you go quiet, it delivers. The sender's receipt names the time the hold ends. Relay the receipt verbatim.

## Report the real receipt

Run the genuine command and report its receipt line verbatim. The CLI calls the hold busy mode. That is DND. The proof is the receipt line, the `fno agents session list` DND column, and the mux `[DND]` marker. Relay a nonzero exit or a `hold NOT off` line verbatim, and claim no DND state. Exit 3 is no provable harness identity.

## Scope

The hold applies to the session that runs the command. When the ask arrives by chat or mail, the lead runs it on the lead's own session. To quiet another session, run the door in that session.

## Not a pause

`fno agents loop control pause-all` and the lead halts stop fleet work. They are not the answer to a user who wants quiet. Codex invokes this skill as `$fno:dnd`.

## Known Limitations and Deferred Work

- No shell command or help text names DND yet: the hold help says "Busy mode" and never DND. See [LIMITATIONS.md](LIMITATIONS.md).

From bllshttng/fno, Apache-2.0.

More from bllshttng/fno

Signals

Stars
2
Forks
0
Open issues
1
Last commit (this folder)
Oct 21, 2026 (9 days ago)
Last release
Oct 23, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from bllshttng

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get dnd running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying dnd?

CallGet help
Cite this page

dnd skill. Agent Mart. https://agentmart.dev/skills/bllshttng-dnd (last updated 2026-10-24)