memory-fabric

A set of project rules for storing and retrieving persistent development notes through Memory Fabric tools.

In plain words
What is it for?
It helps load project context at startup, search memories for a task, save facts, and write a session journal before finishing.
Why use it?
It keeps project facts, directives, and session records in one managed memory system when those tools are available.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/elvirafa/agentic-memory/memory-fabric
Clone the repo
git clone --depth 1 https://github.com/elViRafa/agentic-memory

Made for: Cursor.

Per session 315 This file is loaded in full into every session.
When invoked 315 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00315 $0.00315
Opus 5 $0.00158 $0.00158
Sonnet 5 $0.00063 $0.00063
Haiku 4.5 $0.00032 $0.00032

Measured yesterday against content hash 7547a57af963, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.cursor/rules/memory-fabric.mdc · 19 lines

What it actually says

Memory Fabric — compact Cursor rule

  1. 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-directives rule file) still applies in full; missing MCP tools never excuse ignoring project rules.

  2. Startup: call read_combined_context_tool(cwd="<absolute project root>") unless the MCP Resource memory-fabric://context/<encoded-cwd> was already auto-fetched. Skip a second dump.

  3. Writes: use write_memory_store_tool for facts. Never raw file tools into .ai-memory/ (except hand-curated role: steering directives). Cursor hooks will deny store writes and redirect here.

  4. Retrieval: keyword_search_tool or context_for_task_tool for the task; read_memory_store_tool for a full file. Do not re-dump combined context mid-session.

  5. Session end: write_session_journal_tool before 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

Changes

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.

  1. yesterday First seen · 19 lines · 315 tokens per session scan A 7547a57af963

Subscribe to this mod's changes

memory-fabric is a cursor rule published in the GitHub repository elViRafa/agentic-memory (2 stars, last pushed 13d ago), licensed MIT. It adds 315 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.