mind-mem CLAUDE.md

mind-mem CLAUDE.md is an instructions file for coding agents from star-ga/mind-mem. It costs 4,877 tokens per session, scanned A, original, Apache-2.0.

Project instructions for mind-mem, a persistent memory system for AI agents that combines keyword and meaning-based search.

In plain words
What is it for?
Use them when changing mind-mem's memory storage, search, indexing, daemon, encryption, or MCP tools.
Why use it?
They describe the system's components, configuration, storage backends, security limits, and verification expectations.

Instructions file

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 instructions/star-ga/mind-mem/claude-md
Clone the repo
git clone --depth 1 https://github.com/star-ga/mind-mem

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 mind-mem CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/star-ga/mind-mem/claude-md.svg)](https://agentmods.dev/instructions/star-ga/mind-mem/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/star-ga/mind-mem/claude-md"><img src="https://agentmods.dev/badge/instructions/star-ga/mind-mem/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,877 This file is loaded in full into every session.
When invoked 4,877 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 5.1 $0.04877 $0.04877
Opus 5 $0.02439 $0.02439
Sonnet 5 $0.00975 $0.00975
Haiku 4.5 $0.00488 $0.00488

Measured today against content hash 303082913ba1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mind-mem CLAUDE.md 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 today.

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.

CLAUDE.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MIND-Mem — Persistent AI Memory System

Overview

BM25F + vector hybrid search memory system for AI agents. Published on PyPI: pip install mind-mem

v4.1.1 (released 2026-06-14) — Postgres backend parity: the recall / scan / governance / export / reindex / daemon feature layer was reading the local Markdown corpus + SQLite FTS index and ignoring the configured block_store backend, so Postgres users' blocks were invisible to those features. Added a shared backend-aware storage.iter_active_blocks() + PostgresRecallBackend (BM25 + pgvector RRF), backend-aware/read-only-safe build_index/index_status, pgvector cross-schema detection, daemon cron module path, init_workspace PG setup, MCP _check_workspace backend-aware gate. SQLite/markdown default unchanged (5566 tests, no regression); 81 new both-backend tests. Builds on

v4.1.1 (released 2026-06-05) — security-hardening companion to v4.0.16 (same audit). At-rest encryption relabeled honestly (256-bit HMAC-SHA256 keystream + encrypt-then-MAC, not AES-256/SQLCipher; recall index not encrypted) + 256 MiB encrypt/decrypt DoS cap + .mind-mem-keys 0700 / salt 0600 / decrypt-audit-jsonl 0600. verify_model warns on in-tree-key (self-describing) verification + manifest skips sidecars only at root (no smuggling). MIC-b parser bounds n_syms/n_types. gRPC binds 127.0.0.1 by default (was [::]). tenant_kms (real AESGCM) unchanged.

v4.0.16 (released 2026-06-05) — correctness-hardening release from a six-agent audit. Postgres backend: delete_block silent-rollback (missing deleted_blocks table aborted the txn), diff() AND/OR precedence + active metadata leak, restore() file_path wipe, new ping() health probe surfaced in mm doctor. Replication: ReplicatedPostgresBlockStore now forwards embedding and implements hybrid_search/backfill_embedding/ping. Recall: FTS5 bm25() weight shift (block_id stole statement's weight) + unified _apply_post_filters() so sqlite/vector paths no longer drop lifecycle/event_id/min_maturity. Governance/concurrency: federation.resolve_conflict rowcount guard, apply_proposal re-validate under lock (double-apply), conflict_resolver winner/loser hash mapping, ConnectionManager.close() write-lock, tier-schema ALTER race. MCP: DB errors become structured responses instead of crashing the stdio server. 5465 tests (live PG). No mind-mem-4b retraining. Builds on v4.0.15 (MindLLM backend + token rotation + time-bounded recall + N-08/T-007).

Read the full file on GitHub · 293 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. today Changed 303082913ba1
  2. yesterday Changed · +8 lines · +65 tokens per session abfce6c7122b
  3. 5d ago First seen · 285 lines · 4,812 tokens per session scan A 6d806981abba

Subscribe to this mod's changes

mind-mem CLAUDE.md is an instructions file published in the GitHub repository star-ga/mind-mem (15 stars, last pushed today), licensed Apache-2.0. It adds 4,877 tokens to every session, about $0.0244 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.

Related

Other instructions, from other repositories