presence by default. code by consent.
agentmash sends the room file paths, branch names, the shape of each change (its line counts and the names it touches) and the first 500 characters of a prompt, with an opaque id of the checkout each edit came from. your code stays on your machine unless your room turns diffs on.
what leaves your machine
- who made each edit: your GitHub login, or the email in your git config (your computer’s user name when there is neither).
- file paths and branch names.
- the shape of a change:
+12/-3 lines, touching deletedAt - the first 500 characters of a prompt.
AGENTMASH_HINTS=0keeps yours home. - an opaque id of the checkout each edit came from, so a teammate’s hook can tell your clone from theirs: an HMAC of the hostname and the folder under a key that never leaves your machine, so it names neither.
what never does
- your code, unless the room runs
agentmash diffs on. memory only, never in our database. AGENTMASH_DIFFS=0is your veto, whatever the room says.
when it can't answer, it says so
every hook exits 0 on any failure. it cannot slow you down, and it cannot trap you.
Nobody else has been active in "team repo" in the last 60 min. The coordination server answered normally, so this is a real "no one", not a failure to reach it.
The AgentMash coordination server at https://agentmash.dev is unreachable (fetch failed).
Treat who else is working in this repo as UNKNOWN. This is not the same as "nobody is working on anything" — AgentMash could not ask.
who the room can see
- Claude Code
- every edit and the advisory before it; claims and the MCP tools where a repository registers the server.
- Codex
- every edit, the advisory before it, claims and the MCP tools, once you approve its hooks in
/hooks. - Cursor
- its edits and prompts, live, and the MCP tools. the advisory before an edit comes as a refusal of the first edit, with the reason; the retry goes through. the
cursor-agentCLI runs the same hooks. - GitHub Copilot
- every edit, the advisory before it, its prompts and the MCP tools, in VS Code and its CLI.
- Devin
- its edits, through the Claude Code hooks it runs. whether its agent reads the advisory is still to be verified.
- Amp
- its edits, the files its shell commands change and its prompts, and the MCP tools. the advisory before an edit comes as a refusal of the first edit, with the reason; with Amp's old permission rules on, it only reports.
- Antigravity
- when you ask for it, with
npx agentmash tools add antigravity: its edits, the files its shell commands change and its prompts, and a heads-up at the start of each turn rather than before an edit. - Cline
- its edits and the MCP tools, in VS Code and its CLI, and its prompts in VS Code. the advisory comes just after the edit, not before.
- Crush
- its edits, once the file changes, and the MCP tools. the advisory before an edit comes as a refusal of the first edit, with the reason; its prompts and shell commands aren't seen.
- Factory Droid
- its edits, prompts and the MCP tools. the advisory before an edit comes as a refusal of the first edit, with the reason.
- Gemini CLI
- its edits, prompts and the MCP tools, in folders it trusts. the advisory before an edit comes as a refusal of the first edit, with the reason.
- goose
- its edits and prompts, live, and the MCP tools. the advisory before an edit comes as a refusal of the first edit, with the reason.
- Junie
- its edits, a step after they happen, its prompts in its terminal UI, and the MCP tools. whether its agent reads the advisory before an edit is still to be verified.
- Kilo Code
- its edits, prompts and the MCP tools, in its CLI, VS Code and JetBrains. the advisory before an edit comes as a refusal of the first edit, with the reason.
- Kiro
- its edits, prompts and the MCP tools, in the Kiro IDE and kiro-cli on its V3 engine. the advisory before an edit comes as a refusal of the first edit, with the reason.
- OpenCode
- its edits, prompts and the MCP tools. the advisory before an edit comes as a refusal of the first edit, with the reason.
- OpenHands
- its edits, prompts and the MCP tools, in its CLI and Agent Canvas. the advisory before an edit comes as a refusal of the first edit, with the reason.
- Qwen Code
- its edits, the files its shell commands change, its prompts and the MCP tools. the advisory before an edit comes as a refusal of the first edit, with the reason.
- Continue
- the MCP tools only: it runs no hooks, so its edits don't show in the room.
- Zed
- the MCP tools only: its agent has no hooks, so its edits don't show in the room.
- everyone else, via git
- a post-commit client, in a repository set up with
npx agentmash init: what landed, not what's in progress.
the login connects each one it finds, in its own settings, never in a repository. how each coding agent was checked, as of : the warning before an edit and the reports were tested live in Claude Code, Codex, Cursor, GitHub Copilot (its CLI), Kilo Code and OpenCode, and the MCP tools in Claude Code and Codex; Amp, Cline, Crush, Factory Droid, Gemini CLI, goose, Kiro, OpenHands and Qwen Code are held by our tests against payloads recorded from each tool, not run live yet; Devin, Antigravity, Junie, Continue and Zed rest on their own docs (Devin and Junie partly on our tests too), not tested live yet. /setup says which, for each agent and each part.
the launch list from before agentmash opened keeps a first name and an email. Resend sends our mail, so it sees both.