naumudocs
ConnectorsRepo quickstart

Repo quickstart

Wire a shared repository into your team's Naumu space from your coding agent - one pasteable prompt connects you, whitelists teammates, and opens a review PR.

Updated August 6, 20266 min read

Turn a shared repository into a front door for your team's memory. One pasteable prompt, run from your coding agent, connects you to Naumu, points the repo at your team's space, whitelists the people who ship code, and opens a pull request the team can review. After it merges, every teammate's agent discovers the connection on its own - see Naumu for your repository for the whole story.

This page is for a developer wiring a repo into Naumu. It builds on the local coding agent connection - the prompt runs that setup for you if the tools aren't connected yet.

The prompt

Paste this to your coding agent - Claude Code, Codex, or Cursor. It asks before running each command and never commits directly to a protected branch.

If you're already in Naumu, you can skip the copy-paste: tell the chat you work in a coding agent and Naumu replies with a setup card that opens this same prompt straight in Claude Code, Codex, or Claude Code for VS Code. It's the identical prompt either way.

text
Set up Naumu for this repository. Ask me before running each command, and never commit directly to a protected branch.
1. Connect: if Naumu MCP tools are not available, add the server for this tool, then complete sign-in in the browser (creating my account if needed): Claude Code: claude mcp add --transport http naumu https://naumu.ai/api/mcp - Codex: codex mcp add naumu --transport http https://naumu.ai/api/mcp - Cursor: add "naumu": {"url": "https://naumu.ai/api/mcp"} under mcpServers in .cursor/mcp.json
2. Install the Naumu skill for day-to-day use: npx skills add naumu-ai/skills
3. Call naumu_whoami; if it lists my spaces, use that list to pick an existing space or offer to create one with naumu_create_graph. If it has no space list, fall back to naumu_list_graphs.
4. Find teammates from git history - run this exact command, do not improvise the filter: git log --all --format='%ae|%an|%at' | awk -F'|' -v cut=$(( $(date +%s) - 7776000 )) 'BEGIN{OFS="\t"} $3+0>=cut && tolower($1) !~ /noreply|dependabot|github-actions/ && index(tolower($1),"[bot]")==0 { c[$1]++; if($3+0>l[$1]) l[$1]=$3+0; n[$1]=$2 } END{ pub="@(gmail[.]com|googlemail[.]com|outlook[.]com|hotmail[.]com|live[.]com|yahoo[.]com|icloud[.]com|me[.]com|proton[.]me|protonmail[.]com|pm[.]me|aol[.]com|gmx[.]com|mail[.]com)$"; for(e in c){ g=(tolower(e)~pub)?"CONFIRM":"TEAM"; print g,c[e],l[e],e,n[e] } }' | sort -k1,1 -k2,2nr -k3,3nr - it keeps authors active in the last 90 days, drops bot and noreply addresses, and tags each one TEAM (company address) or CONFIRM (public provider like gmail.com). Show me both groups; never whitelist a CONFIRM address without my explicit per-address confirmation.
5. After I confirm, call naumu_whitelist_members with those emails and repoInit true. Whitelisted teammates auto-join the space when they sign in with that email - no invite emails are sent.
6. Ask me what to call the tracking topic (suggest work-log, kebab-case). Call naumu_list_topics and create it if missing, then create .naumu in the repo root: { "space": "<space id>", "tracking": { "topic": "<slug>", "commitTrailer": true } } - leave commitTrailer true, don't ask.
7. Append to AGENTS.md: Before a substantive task (build, fix, refactor, feature), search the team's Naumu space for prior context on what you are about to touch (naumu_search), and record the work back when done (naumu_delegate). Space id is in .naumu. If Naumu MCP tools are missing, offer setup once - never auto-run: npx skills add naumu-ai/skills, then naumu_resolve_admission with the space id.
8. Open a pull request with these changes plus the installed skill files (.agents/skills/naumu and its .claude/skills/naumu symlink) so the team can review.
9. Offer to seed the space with a short architecture and glossary summary of this repo.

What it does

The prompt is an installer. It connects your agent to Naumu over the remote MCP server (creating your account in the browser if you don't have one), installs the day-to-day skill, and does the repo setup as an agent task: pick or create the team space, scrub git history for teammates, write two small files, and open a PR. Nothing secret is committed - the .naumu file holds the space ID, which is an identifier, not a credential.

The nine steps

  1. Connect. If Naumu's MCP tools aren't available yet, the agent adds the server for your tool and you finish sign-in in the browser - which doubles as signup for a new account.
  2. Install the skill. npx skills add naumu-ai/skills adds the read-and-write loop your agent uses on every task.
  3. Pick a space. The agent calls naumu_whoami; if you already have spaces it asks which one, otherwise it creates one.
  4. Scan git history. It reads recent committers, keeps the last 90 days of active authors, drops bots and noreply addresses, and shows you the list - public-provider addresses (gmail and similar) are grouped separately for you to confirm one by one.
  5. Whitelist teammates. After you confirm, it records the emails; whitelisted teammates auto-join the space when they sign in - no invite emails are sent.
  6. Write .naumu. The agent asks what to call the tracking topic (suggesting work-log), creates it in the space if it doesn't exist, and writes a tiny config at the repo root holding the space ID and that topic.
  7. Update AGENTS.md. A short section tells every teammate's agent to search the space before a substantive task and record the work back when it is done, and to offer setup once if the tools are missing - offer only, never auto-run.
  8. Open a PR. The changes go up as a pull request so the team reviews and merges them - the human merge is the team's consent. The installed skill files go in too (.agents/skills/naumu and its .claude/skills/naumu symlink, which git tracks fine), so a fresh clone gets skill discovery without re-running the installer.
  9. Offer to seed. The agent offers to summarize the repo's architecture and glossary into the space, so the first searches return something useful.

Who gets in

Admission is by identity, checked against verified email when someone signs in - never by a token in the repo.

  • Whitelist (instant). The teammates you confirmed in step 5 join the moment they sign in with that email.
  • Domain wildcard (instant). An admin can set patterns like @yourcompany.com in the space's humans panel; public-provider domains are blocked, so a @gmail.com wildcard is impossible.
  • Request to join (fallback). No match means the newcomer's request lands in the space, and any member approves it with one click. This covers the common case where someone's git email differs from their sign-in email.
  • Seat limits. When a space is at its plan's member cap, a would-be auto-join surfaces as a pending request instead, so an admin can make room or upgrade. See Plans and billing for the caps.

Related

Anything missing?
Tell us what would make these docs better.
CodexAgent skills