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/imayuur/contexthub/contexthub-auto-memorygit clone --depth 1 https://github.com/iMayuuR/contexthubWrote 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/imayuur/contexthub/contexthub-auto-memory)<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>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 | $0.00491 | $0.00491 |
| Opus 5 | $0.00246 | $0.00246 |
| Sonnet 5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
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.
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)
- Session start —
ensure_sessionwith agent name:cursor,claude-code,windsurf,copilot,codex, or your client id. - Before answering —
get_project_context; usesearch_memory/semantic_searchwhen prior context may help. - After each meaningful turn —
record_turnwith concise prompt + response summaries (decisions, bugs, architecture). - Session end —
end_sessionwith 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_rsafor 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_turnover manualsave_memoryfor conversation turns. - On architectural decisions and bugfixes, always
record_turnbefore finishing the reply.
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.
- 4d ago First seen · 57 lines · 491 tokens per session scan A 1fa6cb6370a6
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.
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
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
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…
context-recorder-system
Context Recorder System (记录员系统) - 模块化索引文件.
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.