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.
npx agentmods add rules/yanqiw/comem/cursorgit clone --depth 1 https://github.com/yanqiw/comemWhat 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.
| Model | Per session | Once 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 |
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.
What it actually says
Follow the Coordination Memory protocol in AGENTS.md (the section between the
coordination-memory markers).
completed_gate_passedis not accepted truth — only an integratoraccept_eventmakes work accepted.- Claim assignments before working; carry the current
base_revisionon mutating calls. - Orient with
get_team_board/get_assignment_detailbefore acting. - For loop-dispatched work, read
metadata.context_refs, obeyallowed_pathsandacceptance_criteria, usemetadata.session_bind.target_actor_idas the intended worker binding before any run exists, and keep run communication metadata current withrecord_run_binding.
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.
- yesterday First seen · 18 lines · 162 tokens per session scan A af180a556dc6
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.
Other cursor rules, from other repositories
cursorrules
mind-mem workspace: /mind-mem Use mm inject --agent cursor before answering.
050-plan
When the user types /plan or asks to create a project plan, feature PRD, or retrospective.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
token-efficiency
Token efficiency rules - eliminate waste in AI output, enforce read-before-write, prevent iteration cycles.
orchestrator-main
Rules for the main orchestrator agent in multi-agent workflows.
project
4DA project rules and conventions.