cursorrules

A set of Cursor rules for the Immersive Commons skills and SDK repository. Cursor is a coding editor with an AI assistant, and these rules tell that assistant how to work in this project.

In plain words
What is it for?
Use it when Cursor edits or calls the Immersive Commons agent API, including its skills, SDKs, and integration files.
Why use it?
It helps prevent incorrect API calls by pointing the assistant to the repository contract, approved tools, connection method, and authentication limits.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/immersive-commons/ic-skills/cursorrules
Clone the repo
git clone --depth 1 https://github.com/Immersive-commons/ic-skills

Made for: Cursor.

Per session 351 This file is loaded in full into every session.
When invoked 351 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00351 $0.00351
Opus 5 $0.00176 $0.00176
Sonnet 5 $0.00070 $0.00070
Haiku 4.5 $0.00035 $0.00035

Measured yesterday against content hash d5a05de50efb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 yesterday.

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.

.cursorrules · 25 lines

What it actually says

Immersive Commons — agent rules (Cursor, legacy format)

Canonical version: .cursor/rules/immersive-commons.mdc · Full contract: AGENTS.md

You are working in the public skills + SDK repo for the Immersive Commons agent API (https://www.immersivecommons.com — Floor 10, Frontier Tower SF).

Rules:

  1. Read AGENTS.md before calling the API — it is the sourced contract for every endpoint, tool, and scope. Machine-readable docs on the live site (/.well-known/mcp.json, /.well-known/ai-agent.json, /openapi.json, /llms.txt) always win over prose in this repo.
  2. Prefer the MCP transport at https://www.immersivecommons.com/api/mcp. 10 tools are public (no auth) — smoke-test with ic_signal_get_latest. REST (/openapi.json) and A2A (/api/a2a) expose the same capabilities.
  3. Never invent endpoints, tool names, or scopes. The tool catalog in /.well-known/mcp.json is exhaustive.
  4. Auth: per-user agt_* bearer tokens, minted only through the human-approved device-code flow (https://www.immersivecommons.com/auth.md). Do not attempt to self-mint, scrape, or hardcode tokens.
  5. Skills in skills//SKILL.md are self-contained walkthroughs with YAML frontmatter (name, description) — keep that contract when editing.
  6. Writes to the live API (RSVPs, submissions, bookings, sends) are consequential: confirm with the human before firing them.
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. yesterday First seen · 25 lines · 351 tokens per session scan A d5a05de50efb

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository Immersive-commons/ic-skills (0 stars, last pushed 1mo ago), licensed MIT. It adds 351 tokens to every session, about $0.0018 per session on Opus 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 2026-08-31.