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/karstom/simplegraph-agentic/memorygit clone --depth 1 https://github.com/karstom/simplegraph-agenticWhat 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 | $0.00291 | $0.00291 |
| Opus 5 | $0.00146 | $0.00146 |
| Sonnet 5 | $0.00058 | $0.00058 |
| Haiku 4.5 | $0.00029 | $0.00029 |
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
simplegraph-agentic Memory Graph
Session start (mandatory):
CRITICAL: You MUST read (e.g. using a file reading tool) core/graph_index.md as your very first action in every conversation, without exception.
It is ~40 lines. Do not skip this step. Do not load the full graph.
Rules
- Read
core/graph_index.mdfirst, every session. - Use the Task Routing table in
graph_index.mdto decide which detail files to load. Only load files relevant to the current task — not all files. - Before modifying any component, check its edges for
VIOLATED_BYandWATCHLISTlinks. Any Regression withREGRESSED_N_TIMES >= 2indicates high-risk code — proceed carefully. - After fixing a bug, making an architectural decision, or identifying a dangerous code area,
update the graph in the same commit. See
core/HOW_TO_UPDATE.mdfor the protocol. - If the graph contradicts the code, flag the discrepancy before implementing anything.
Multi-Repo
If core/graph_index.md lists a shared graph path, read that index too when working
across repo boundaries.
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 · 27 lines · 291 tokens per session scan A a2888317a55b
memory is a cursor rule published in the GitHub repository karstom/simplegraph-agentic (5 stars, last pushed 5d ago), licensed MIT. It adds 291 tokens to every session, about $0.0015 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
You have the AI Mind Map MCP server connected. It is a persistent code memory system that eliminates redundant file re-reading and context loss between sessions.
ccmds
Use when user asks about docs, documentation, guides, references, how-to, setup instructions, API reference, configuration, or says "check the docs", "what do the docs say", "find in documentation". Provides markdown search via ccmds CLI.
meta-rule-authoring
Meta-rule that instructs every LLM-powered agent how to write, store, and compile new “source-of-truth” rules. All new rules must live in ./agent-rules/ as Markdown files with the same front-matter structure shown here. After a rule is added or changed, the agent must run ./translaterules.ts to regenerate…
prototype-structure
Defines how every AI prototype must be laid out in the repository.
agent-identity
身份与输出规范 — 身份元数据 + 飞书卡片输出限制.
cursorrules
Cursor rule "cursorrules" from me2resh/agent-decision-record, covering agent decision records (agdr) — cursor rules, purpose, see: https://github.com/me2resh/agent-decision-record, decision detection and adding a new dependency → stop, document decision first.