rowboat-spaces

rowboat-spaces is a skill for Claude Code, Codex from rowboatlabs/rowboat. It costs 61 tokens per session (829 once invoked), scanned A, original, Apache-2.0.

A set of rules for participating in Rowboat Spaces, a team chat where people and software agents work together. It explains how to read threads, reply, mention members, and hand work to another agent.

In plain words
What is it for?
Use it when a request comes from Rowboat Spaces or when the agent must read more of a thread, mention someone, delegate work, or post a message.
Why use it?
It prevents messages from going to the wrong conversation or failing to notify the intended person. It also sets expectations for keeping chat replies short and using exact mention links.

Skill for Claude CodeCodex

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

Good fit Use it when a request comes from Rowboat Spaces or when the agent must read more of a thread, mention someone, delegate work, or post a message.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rowboatlabs/rowboat/rowboat-spaces
About the project

Rowboat is an open-source personal AI assistant that organizes email, meetings, conversations, and other work into a linked knowledge graph, then helps people act on that information. It provides work areas for email, notes, browsing, coding, meeting transcription, and collaboration with background agents, for individual users or teams.

rowboatlabs/rowboat · 17,996 stars · on GitHub · rowboatlabs.com

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 rowboatlabs/rowboat --skill rowboat-spaces
Clone the repo
git clone --depth 1 https://github.com/rowboatlabs/rowboat

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 rowboat-spaces

README.md
[![agentmods](https://agentmods.dev/badge/skills/rowboatlabs/rowboat/rowboat-spaces/github.svg)](https://agentmods.dev/skills/rowboatlabs/rowboat/rowboat-spaces)
Your own site
<a href="https://agentmods.dev/skills/rowboatlabs/rowboat/rowboat-spaces"><img src="https://agentmods.dev/badge/skills/rowboatlabs/rowboat/rowboat-spaces/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 rowboat-spaces

Your own site · 80×15
<a href="https://agentmods.dev/skills/rowboatlabs/rowboat/rowboat-spaces"><img src="https://agentmods.dev/badge/skills/rowboatlabs/rowboat/rowboat-spaces.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 829 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.
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 $0.00061 $0.00829
Opus 5.5 $0.00024 $0.00332
Sonnet 5.5 $0.00012 $0.00166
Haiku 4.5 $0.00006 $0.00083

Measured 5d ago against content hash 920f3b4bf004, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rowboat-spaces 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 5d 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.

skills/rowboat-spaces/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rowboat Spaces

Rowboat Spaces is a team chat. People and agents are both members, and you are one of them. Every request reaches you from a message in a space or a direct message (DM), and your reply is posted as you.

Where you are

  • A conversation is a thread. You were asked in one, and your answer goes in that thread. Start a new top-level message, or post in another space or DM, only when someone asks you to.
  • In a space, a mention brings you in. In a DM with you, every message does, mention or not.
  • Replies render as Markdown. Keep them short enough to read in a chat.
  • You see what is new. Each request comes with the thread's messages since you last heard from it. Read the rest with the tools below when you need it.

Mentions

A mention is a token: a Markdown link whose target holds the member's id.

[@Harsh](#member:01J8KQ4T3M9V2B7XCH0RDQ5AEF)
  • Only a token reaches anyone. A bare @Harsh is plain text: it notifies no one and invokes no agent.
  • Copy tokens exactly from what you read: the messages, and the authors written as tokens beside them, including whoever asked you. Never type an id from memory. For someone not in front of you, find their id with list_members.
  • The id in a token is the member id the tools take: open_direct with it opens your DM with that person.
  • [@here](#here) addresses everyone in the space. [#Design](#space:<spaceId>) points at a space and notifies no one.
  • A token inside code is a quote, not a mention.

When to mention

A mention hands someone the thread: a person is notified, and an agent starts a turn on it.

  • Agents see only messages that mention them. A question or request to another agent reaches it only with its token, even when it is in the same thread.
  • Whenever you need a person or an agent to act or answer, mention them, whoever asked you included. To talk about someone, write their name without a token.
  • Never mention to thank, acknowledge or sign off. Each mention starts another turn, and two agents mentioning each other never stop.
  • Hand-offs stop at three hops. Past that, Rowboat refuses the mention and says why under your message. get_invocations shows what agents are doing in a thread.
  • When you hand work to another agent, say so in your reply, so the people in the thread know who has it.

Read the full file on GitHub · 54 lines

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. 5d ago First seen · 54 lines · 61 tokens per session scan A 920f3b4bf004

Subscribe to this mod's changes

rowboat-spaces is a skill published in the GitHub repository rowboatlabs/rowboat (17,996 stars, last pushed yesterday), licensed Apache-2.0. It adds 61 tokens to every session and 829 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-02.