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/elViRafa/agentic-memoryWrote 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/elvirafa/agentic-memory/memory-fabric)<a href="https://agentmods.dev/rules/elvirafa/agentic-memory/memory-fabric"><img src="https://agentmods.dev/badge/rules/elvirafa/agentic-memory/memory-fabric/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/elvirafa/agentic-memory/memory-fabric"><img src="https://agentmods.dev/badge/rules/elvirafa/agentic-memory/memory-fabric.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 | $0.00315 | $0.00315 |
| Opus 5.5 | $0.00126 | $0.00126 |
| Sonnet 5.5 | $0.00063 | $0.00063 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
memory-fabric 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 2mo 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
Memory Fabric — compact Cursor rule
-
If the memory-fabric MCP tools are NOT available in this session, skip this memory protocol entirely — do NOT substitute another memory system for it. Any Project Directives block (in this file, or in a generated
project-directivesrule file) still applies in full; missing MCP tools never excuse ignoring project rules. -
Startup: call
read_combined_context_tool(cwd="<absolute project root>")unless the MCP Resourcememory-fabric://context/<encoded-cwd>was already auto-fetched. Skip a second dump. -
Writes: use
write_memory_store_toolfor facts. Never raw file tools into.ai-memory/(except hand-curatedrole: steeringdirectives). Cursor hooks will deny store writes and redirect here. -
Retrieval:
keyword_search_toolorcontext_for_task_toolfor the task;read_memory_store_toolfor a full file. Do not re-dump combined context mid-session. -
Session end:
write_session_journal_toolbefore the last response (skip only trivial Q&A).
Full protocol (on demand): .agents/rules/memory-store.md
Dreaming parameters (on demand): .agents/rules/dreaming.md
Which tool when: .agents/skills/agent-router/SKILL.md
Available skills: .agents/skills/INDEX.md
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.
- 2mo ago First seen · 19 lines · 315 tokens per session scan A 7547a57af963
memory-fabric is a cursor rule published in the GitHub repository elViRafa/agentic-memory (1 stars, last pushed 20d ago), licensed MIT. It adds 315 tokens to every session, about $0.0013 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
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Search dreamd at the start of a task and quote a hit. Append when the user corrects you or states a decision.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.
memsprout
Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.