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/acn-ericlaw/agent-memory/cursorrulesgit clone --depth 1 https://github.com/acn-ericlaw/agent-memoryWhat 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 | $0.00064 | $0.00064 |
| Opus 5 | $0.00032 | $0.00032 |
| Sonnet 5 | $0.00013 | $0.00013 |
| Haiku 4.5 | $0.00006 | $0.00006 |
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.
What it actually says
agent-memory — both a shared AI memory layer and an AI-enablement / migration tool (no-code, markdown).
Follow memory/PROTOCOL.md first. AGENTS.md is its one-line universal discovery shim; the protocol selects internal-memory work versus AI-enabling another repository.
Identify yourself as Cursor in all session logs.
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 · 7 lines · 64 tokens per session scan A ed49681465f7
cursorrules is a cursor rule published in the GitHub repository acn-ericlaw/agent-memory (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 64 tokens to every session, about $0.0003 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
reelier
When to use the Reelier MCP tools (reelierscan, reelierfromsession, reelierreplay, reelierdiff, reelierpush) to freeze and replay deterministic tool-call workflows.
write-migration
Author an idempotent, state-detecting migration under scripts/migrations/ for a breaking llm-wiki-memory change. Use when shipping a breaking change to the engine, or when asked to write a migration / upgrade path. Replaces the retired release-runbook flow.
debug-capture-pipeline
Debug llm-wiki-memory capture/recall — flush breadcrumbs, daily-vs-compile lag, failed-distill stash recovery, embedding cache, hook wiring. Use when memory didn't capture, doesn't recall, or a hook/cron looks broken.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
lemoncrow.execute
LemonCrow execute mode reference for Cursor.
cursorrules
You are an expert software engineer and architect. You are part of a team, but your memory is reset after every session. To compensate for this, you rely on a "Memory Bank" stored in the memory/ directory.