01-ownership

A rule that limits each coding agent to the files and folders it owns.

In plain words
What is it for?
Defining ownership by path, checking whether a change is allowed, and routing cross-owner work through journals, approvals, proposals, or the operator.
Why use it?
It prevents overlapping edits and accidental changes to another agent's work. Changes outside an agent's ownership require a request, approval, or proposal.

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/anshulixyz/multi-agent-loop-kit/01-ownership
Clone the repo
git clone --depth 1 https://github.com/anshulixyz/multi-agent-loop-kit

Made for: Cursor.

Per session 238 This file is loaded in full into every session.
When invoked 238 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 $0.00238 $0.00238
Opus 5 $0.00119 $0.00119
Sonnet 5 $0.00048 $0.00048
Haiku 4.5 $0.00024 $0.00024

Measured 3d ago against content hash 4dd4326eb6ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

01-ownership 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 3d 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.

.cursor/rules/01-ownership.mdc · 36 lines

What it actually says

Ownership rule

Every coding agent may edit only its owned paths.

If a change requires editing another owner's path, stop and create one of:

  • journal task for that owner
  • approval request
  • proposal
  • operator ask

Do not perform drive-by edits in another owner’s path.


Ownership matrix

Replace with repo-specific paths.

Path Owner Notes
apps/web/** frontend UI
apps/api/** backend API/backend
packages/types/** operator frozen contracts
packages/mocks/** agentkit mock fixtures
.github/** ops CI
.cursor/rules/** operator persistent rules
agents-status/<codename>.md <codename> own journal only
agents-status/proposals/** shared protocol author creates, operator decides
agents-status/approvals/** shared protocol requester creates, operator decides
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. 3d ago First seen · 36 lines · 238 tokens per session scan A 4dd4326eb6ec

Subscribe to this mod's changes

01-ownership is a cursor rule published in the GitHub repository anshulixyz/multi-agent-loop-kit (5 stars, last pushed 2mo ago), licensed MIT. It adds 238 tokens to every session, about $0.0012 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.