mind-mem-development

mind-mem-development is a skill for Claude Code, Codex from star-ga/mind-mem. It costs 12 tokens per session (477 once invoked), scanned A, original, Apache-2.0.

A development guide for MIND-Mem, a Python package that stores, searches, updates, and restores structured memories. It describes the package layout, tests, architecture, and its MCP server, which exposes tools to coding agents.

In plain words
What is it for?
Use it when developing or reviewing MIND-Mem code, especially retrieval, memory updates, SQLite storage, snapshots and rollback, intent classification, diagnostics, or MCP server integrations.
Why use it?
It helps an agent work within MIND-Mem's existing design and avoid guessing how its memory search, storage, snapshots, or server tools work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

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 skills/star-ga/mind-mem/mind-mem-development
Any agent
npx skills add star-ga/mind-mem --skill mind-mem-development
Clone the repo
git clone --depth 1 https://github.com/star-ga/mind-mem

Made for: Claude Code, Codex.

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-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/star-ga/mind-mem/mind-mem-development.svg)](https://agentmods.dev/skills/star-ga/mind-mem/mind-mem-development)
Your own site
<a href="https://agentmods.dev/skills/star-ga/mind-mem/mind-mem-development"><img src="https://agentmods.dev/badge/skills/star-ga/mind-mem/mind-mem-development.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 477 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 5.1 $0.00012 $0.00477
Opus 5 $0.00006 $0.00238
Sonnet 5 $0.00002 $0.00095
Haiku 4.5 $0.00001 $0.00048

Measured 6d ago against content hash f47fa134e65f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mind-mem-development 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 6d 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.

.agents/skills/mind-mem-development/SKILL.md · 50 lines

What it actually says

MIND-Mem Development

Package

  • PyPI: pip install mind-mem
  • Source layout: src/mind_mem/
  • Tests: pytest, 3610 passing
  • CI: GitHub Actions, 3 OS × 4 Python versions (16 matrix jobs)

Architecture

  • BM25F retrieval with Porter stemming + RM3 query expansion
  • Hybrid BM25+Vector search with RRF fusion (sqlite-vec)
  • A-MEM block metadata evolution
  • 9-type intent router with adaptive confidence weights
  • ConnectionManager: thread-safe SQLite pool with WAL
  • BlockStore protocol: decoupled block access
  • Delta-based snapshot rollback

MCP Server (81 tools)

Grouped surfaces (full list in docs/api-reference.md and src/mind_mem/mcp_server.py): recall, hybrid_search, prefetch, propose_update, approve_apply, rollback_proposal, scan, list_contradictions, reindex, index_stats, create_snapshot, list_snapshots, restore_snapshot, briefing, category_summary, cross_encoder_rerank, find_similar, memory_evolution, delete_memory, export_memory, import_memory, intent_classify, retrieval_diagnostics, get_mind_kernel, list_mind_kernels, verify_chain, audit_replay, tier_decay_apply, encrypt_status, alerts_subscribe, and more (57 total).

Key Files

  • src/mind_mem/mcp_server.py — MCP server (57 @mcp.tool entries)
  • src/mind_mem/retrieval/ — search engine (bm25, vector, hybrid)
  • src/mind_mem/governance/ — contradiction detection, drift analysis
  • src/mind_mem/blocks/ — block store, parser, evolution
  • tests/ — comprehensive test suite

Conventions

  • Python 3.10+, type hints everywhere
  • Docstrings: Google style
  • No dynamic allocation in hot paths
  • All SQL queries parameterized
  • Config: mind-mem.json (not mem-os.json)
  • Auth header: X-MindMem-Token
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. 6d ago First seen · 50 lines · 12 tokens per session scan A f47fa134e65f

Subscribe to this mod's changes

mind-mem-development is a skill published in the GitHub repository star-ga/mind-mem (15 stars, last pushed yesterday), licensed Apache-2.0. It adds 12 tokens to every session and 477 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 2026-08-30.