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.
git clone --depth 1 https://github.com/karstom/simplegraph-agenticWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/karstom/simplegraph-agentic/memory)<a href="https://agentmods.dev/rules/karstom/simplegraph-agentic/memory"><img src="https://agentmods.dev/badge/rules/karstom/simplegraph-agentic/memory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/karstom/simplegraph-agentic/memory"><img src="https://agentmods.dev/badge/rules/karstom/simplegraph-agentic/memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00382 | $0.00382 |
| Opus 5.5 | $0.00153 | $0.00153 |
| Sonnet 5.5 | $0.00076 | $0.00076 |
| Haiku 4.5 | $0.00038 | $0.00038 |
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 1mo ago.
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 core/graph_index.md (or call simplegraph_index if MCP is enabled) 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.md(or callsimplegraph_index) first, 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 or file:
- If MCP is configured: call
simplegraph_check_files({files: ["path/to/file"]}). - Without MCP: check edge links in the loaded graph for
VIOLATED_BYandWATCHLISTlinks. Any Regression withREGRESSED_N_TIMES >= 2indicates high-risk code — proceed carefully.
- If MCP is configured: call
- Before generating code: call
simplegraph_anti_patterns()(or checkcore/anti_patterns.md). - 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. (Usesimplegraph_add_node/simplegraph_update_nodeif MCP is configured). - 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.
- 1mo ago Changed · +4 lines · +91 tokens per session 78201dd5f306
- 1mo ago 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 4d ago), licensed MIT. It adds 382 tokens to every session, about $0.0015 per session on Opus 5.5. 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
team-brain
Team Brain sync mode — one start per ticket, then live merge-safe crew memory. Always-on when .team-brain exists or work mentions an initiative/Jira key.
engineer-brain
Your engineering brain context — always-on awareness of work patterns, career history, expertise, and current focus. Loaded automatically for personalized assistance.
aictx
Cursor rule "aictx" from oldskultxo/aictx, covering aictx, priority model, default loop, inspection and advanced tools and what to record.
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.
memory-protocol
A protocol for storing and retrieving project memories from files, using a command-line memory tool. It records decisions, preferences, dates, tasks, and other useful history for later conversations.
user-context
A template for recording information about the user, including their work, skills, language, and communication preferences.