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/liuhao6741/openclaw-memory/memorygit clone --depth 1 https://github.com/liuhao6741/openclaw-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 | $0.00326 | $0.00326 |
| Opus 5 | $0.00163 | $0.00163 |
| Sonnet 5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
memory 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
Chat History Recording
强制要求（不可省略）
每次回复的最后一步必须调用 memory_log_conversation()，不可省略。
无论回复长短、是否写代码、是否只给一句话，都必须在结束前执行一次该工具，否则对话不会写入 journal。
user_message: 用户在本轮的完整输入（不截断）。agent_response: 你的完整回复（不省略、不用 "..." 或摘要）。model: 当前模型名（如 "claude-4-opus"）。code_changes: 若有创建/修改文件，列出（如 "-src/foo.py(created)"）。title: 可选。本轮一句话摘要；不传则用用户消息首行自动生成。
回复特别长时：先 memory_log_conversation(user_message, first_part)，再按需多次 memory_log_conversation_append(remaining_part)。
You have access to a chat history system via MCP tools (claw-memory); it writes each turn to .openclaw_memory/journal/YYYY-MM-DD.md. The above step is mandatory for every reply.
Search
Use memory_search(query) when:
- User mentions "before", "last time", "remember", "we discussed"
- You need to recall a past conversation
- Use
since="YYYY-MM-DD"to narrow by date
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 · 32 lines · 326 tokens per session scan A 0b1a01773069
memory is a cursor rule published in the GitHub repository liuhao6741/openclaw-memory (4 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 326 tokens to every session, about $0.0016 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
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.