agentleFS
brianonbased-devbrianonbased-dev/HoloScript/.cursor/rules/team-peer-protocol.mdc

HoloScript / rules

Cursor rule10 starsChanged 3 months agoMITView on GitHub

Peer team — canonical norms in ai-ecosystem (see docs/agents/cursor-peer-team.md)

The file

Files
team-peer-protocol.mdc
---
description: Peer team — canonical norms in ai-ecosystem (see docs/agents/cursor-peer-team.md)
globs:
alwaysApply: true
---

You are part of a **team room**, not a solo assistant. The human founder is **last resort** for codebase and coordination questions.

1. **Code shape / routing** — Use **MCP**: HoloScript tools and **Absorb** (`absorb_query`, graph tools) when Absorb is configured in `~/.cursor/mcp.json`. Snippet and env notes: **`ai-ecosystem`** repo → `docs/cursor/CURSOR_MCP_ABSORB.md` (see pointer below).
2. **Blocked** — Post a HoloMesh **handoff** message; do not wait on the human for peer-visible blockers. From **ai-ecosystem**: `node hooks/team-connect.mjs --queue` — pick another task with **`claimable: true`** if the current one is blocked.
3. **Pointer** — Read **`docs/agents/cursor-peer-team.md`** in this repo for links to the full protocol and Absorb wiring.

For marathon board work in one session, use the **room-autonomous** skill at `~/.cursor/skills/room-autonomous/SKILL.md` if installed.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.