memkernel-memory

A protocol for storing project decisions, conventions, code details, and session checkpoints in MemKernel, a memory service for development projects.

In plain words
What is it for?
It is for recalling earlier decisions, saving architecture and interface details, and recording what was completed, what remains, and which questions are open.
Why use it?
It reduces repeated work and helps the coding agent recover important context after a new session or a context reset.

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/gosha70/code-copilot-team/memkernel-memory
Clone the repo
git clone --depth 1 https://github.com/gosha70/code-copilot-team

Made for: Cursor.

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 338 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00022 $0.00338
Opus 5 $0.00011 $0.00169
Sonnet 5 $0.00004 $0.00068
Haiku 4.5 $0.00002 $0.00034

Measured 2d ago against content hash b23402ef2098, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memkernel-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 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.

adapters/cursor/.cursor/rules/memkernel-memory.mdc · 49 lines

What it actually says

MemKernel Memory

Use this rule only when the memkernel MCP server is configured for the project.

Purpose

MemKernel gives the project persistent memory across sessions and compaction events. Use it to retain decisions, conventions, important code context, and structured session checkpoints.

When To Recall

  • At the start of a new session, call recall for the current task or topic.
  • After compaction, recover the latest checkpoint first, then broaden recall.
  • Before repeating earlier work, recall prior decisions instead of guessing.

What To Retain

  • decision: architecture choices, tradeoffs, dependency decisions
  • convention: naming rules, style decisions, workflow expectations
  • code: important interfaces, schemas, contracts, or code snapshots
  • episode: session events and structured checkpoints

Checkpoint Pattern

Before compaction, retain a checkpoint with:

  • what was completed
  • active constraints
  • current task
  • next steps
  • open questions

Use checkpoint=true for these records so they can be recovered separately.

Working Rules

  • Be specific. Vague memories are hard to retrieve later.
  • Prefer one focused memory per decision or convention.
  • Use get(ref_id) when a recall result looks relevant but the preview is not enough.
  • Do not spam duplicate memories. retain is idempotent for identical content and type.
  • Treat recalled content as context to verify, not as unquestionable truth.
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 · 49 lines · 22 tokens per session scan A b23402ef2098

Subscribe to this mod's changes

memkernel-memory is a cursor rule published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 338 once invoked, about $0.0001 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.