cursor

A set of coding-agent rules for the Coordination Memory protocol, a process for tracking shared work among agents. It requires explicit acceptance records and assignment details before agents act.

In plain words
What is it for?
Use it when agents work together on the same project and need tracked assignments, revision information, worker bindings, run updates, and acceptance criteria.
Why use it?
It prevents an agent's report or a completed check from being mistaken for accepted work. It also keeps agents oriented around the current shared state and allowed files.

Cursor rule

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/yanqiw/comem/cursor
Clone the repo
git clone --depth 1 https://github.com/yanqiw/comem
Per session 162 This file is loaded in full into every session.
When invoked 162 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 $0.00162 $0.00162
Opus 5 $0.00081 $0.00081
Sonnet 5 $0.00032 $0.00032
Haiku 4.5 $0.00016 $0.00016

Measured yesterday against content hash af180a556dc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor 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.

src/coordination_memory_mcp/templates/cursor.mdc · 18 lines

What it actually says

Follow the Coordination Memory protocol in AGENTS.md (the section between the coordination-memory markers).

  • completed_gate_passed is not accepted truth — only an integrator accept_event makes work accepted.
  • Claim assignments before working; carry the current base_revision on mutating calls.
  • Orient with get_team_board / get_assignment_detail before acting.
  • For loop-dispatched work, read metadata.context_refs, obey allowed_paths and acceptance_criteria, use metadata.session_bind.target_actor_id as the intended worker binding before any run exists, and keep run communication metadata current with record_run_binding.
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 · 18 lines · 162 tokens per session scan A af180a556dc6

Subscribe to this mod's changes

cursor is a cursor rule published in the GitHub repository yanqiw/comem (1 stars, last pushed 1mo ago), licensed MIT. It adds 162 tokens to every session, about $0.0008 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.