contexthub-auto-memory

contexthub-auto-memory is a cursor rule for Cursor from iMayuuR/contexthub. It costs 491 tokens per session, scanned A, original, MIT.

Rules for securely storing and retrieving project memory through ContextHub, a local encrypted memory system for coding agents.

In plain words
What is it for?
Starting and ending agent sessions, retrieving earlier project context, and recording important decisions, bugs, and conventions.
Why use it?
They define when project context must be loaded or saved and help prevent secrets such as passwords, tokens, and private keys from entering memory.

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/imayuur/contexthub/contexthub-auto-memory
Clone the repo
git clone --depth 1 https://github.com/iMayuuR/contexthub

Made for: Cursor.

Wrote 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.

agentmods badge for contexthub-auto-memory

README.md
[![agentmods](https://agentmods.dev/badge/rules/imayuur/contexthub/contexthub-auto-memory.svg)](https://agentmods.dev/rules/imayuur/contexthub/contexthub-auto-memory)
Your own site
<a href="https://agentmods.dev/rules/imayuur/contexthub/contexthub-auto-memory"><img src="https://agentmods.dev/badge/rules/imayuur/contexthub/contexthub-auto-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 491 This file is loaded in full into every session.
When invoked 491 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 $0.00491 $0.00491
Opus 5 $0.00246 $0.00246
Sonnet 5 $0.00098 $0.00098
Haiku 4.5 $0.00049 $0.00049

Measured 4d ago against content hash 1fa6cb6370a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

contexthub-auto-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 4d 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.

.cursor/rules/contexthub-auto-memory.mdc · 57 lines

What it actually says

ContextHub — Secure Auto-Memory Policy

ContextHub stores encrypted project memory locally (AES-256-GCM). Agents must use MCP tools — no shell logging or shell profile changes.

Required workflow (every session)

  1. Session startensure_session with agent name: cursor, claude-code, windsurf, copilot, codex, or your client id.
  2. Before answeringget_project_context; use search_memory / semantic_search when prior context may help.
  3. After each meaningful turnrecord_turn with concise prompt + response summaries (decisions, bugs, architecture).
  4. Session endend_session with the active session id.

When to call record_turn automatically (do not ask the user)

  • Architectural or design decisions
  • Bug root cause and fix
  • Non-obvious repo conventions
  • Security-relevant behavior
  • Breaking changes

Skip: small talk, pure formatting, duplicate facts already stored.

Security (mandatory)

  • Never read or output .contexthub/.keyfile
  • Never store API keys, passwords, tokens, or private keys
  • Never scan .env, .pem, .key, id_rsa for memory content
  • Use repo-relative paths only

Tool cheat sheet

Goal Tool
Start session ensure_session
Save a turn record_turn
Single note save_memory
Unified query contexthub_query
Find context search_memory, semantic_search
Code graph stats get_code_graph_stats
Related symbols get_related_symbols
Blast radius get_blast_radius
Trace path trace_code_path
Search by code search_memory_by_code
Full policy text get_agent_policy

Cursor-specific

  • ContextHub MCP must be enabled (see .cursor/mcp.json).
  • Prefer record_turn over manual save_memory for conversation turns.
  • On architectural decisions and bugfixes, always record_turn before finishing the reply.
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. 4d ago First seen · 57 lines · 491 tokens per session scan A 1fa6cb6370a6

Subscribe to this mod's changes

contexthub-auto-memory is a cursor rule published in the GitHub repository iMayuuR/contexthub (0 stars, last pushed 3mo ago), licensed MIT. It adds 491 tokens to every session, about $0.0025 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.