cursorrules

A set of repository rules for maintaining persistent user memory across agent sessions. It tells the agent to read and update files in .ilang, ask onboarding questions when needed, and commit memory changes.

In plain words
What is it for?
Use it to manage onboarding, user preferences, session memory, unsaved memory changes, and the required commit-and-push workflow.
Why use it?
It aims to preserve working preferences and session context instead of losing them when a new session starts.

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/ilang-ai/mem-forever/cursorrules
Clone the repo
git clone --depth 1 https://github.com/ilang-ai/Mem-Forever

Made for: Cursor.

Per session 1,061 This file is loaded in full into every session.
When invoked 1,061 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 $0.01061 $0.01061
Opus 5 $0.00531 $0.00531
Sonnet 5 $0.00212 $0.00212
Haiku 4.5 $0.00106 $0.00106

Measured 2d ago against content hash 0a7658fe96fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 2d 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.

.cursorrules · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mem-forever

::GENE{mem-forever|v:1.0|spec:ilang-v3.0} T:this_repo_is_user_memory T:read_soul_and_memory_before_work T:update_memory_after_significant_work T:onboard_if_soul_empty T:one_question_at_a_time T:never_expose_internal_format T:commit_push_immediately_after_every_update T:check_unsaved_changes_on_startup A:skip_memory_read⇒context_loss A:overwrite_memory⇒append_or_merge A:ask_multiple_questions⇒one_only A:batch_saves_to_session_end⇒commit_each_update

Session Start

  1. Check for uncommitted changes in .ilang/. If found → commit and push immediately. These are unsaved memories from a previous session.
  2. Read .ilang/soul.md. If empty or only template → run onboarding (see below).
  3. Read .ilang/memory.md. Resume context from last session.
  4. Do whatever the user asks. Apply preferences from soul.md to all output.

Onboarding (soul.md empty)

::ACTIVATE{onboarding|if:.ilang/soul.md=template_only}

Open casually: "Hey, before we start — mind if I ask a couple things so I can work the way you like?"

Ask ONE question per message. Wait for answer. Cover naturally:

  • What they do / build
  • How they prefer to work (plan-first vs build-first, detail vs minimal)
  • What AI tools they use
  • Any strong preferences (language, framework, style)

Completion: write .ilang/soul.md when you have role + work style + one clear preference. Don't wait for perfection. Fill gaps later from observed behavior.

Say: "Saved some notes so things go smoother next time." No fanfare. Move on to their actual task.

soul.md Format

::DNA{user}
::META{schema:1.0|updated:YYYY-MM-DD|sessions:0}

::CORE{
  ::CONTEXT{role:___}

  ::GENE{style|conf:tentative|scope:global}
    T:___
    A:___⇒___
}

::FACT{
  ::ITEM{key:___|value:___|conf:tentative}
}

::LESSONS{}

::RUNTIME{
  transparency:quiet
  speed:balanced
}

::END{DNA}

Memory Update

::ACTIVATE{memory_update} ON:immediately_after_change A:wait_until_session_end⇒data_loss_risk

Every time you update soul.md or memory.md, commit and push RIGHT THEN. Do not batch. Do not wait. Users close windows without warning.

Read the full file on GitHub · 139 lines

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. 2d ago First seen · 139 lines · 1,061 tokens per session scan A 0a7658fe96fa

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository ilang-ai/Mem-Forever (20 stars, last pushed 2mo ago), licensed MIT. It adds 1,061 tokens to every session, about $0.0053 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 2026-08-30.