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 instructions/star-ga/mind-mem/claude-mdgit clone --depth 1 https://github.com/star-ga/mind-memWrote 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/instructions/star-ga/mind-mem/claude-md)<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>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 5.1 | $0.04877 | $0.04877 |
| Opus 5 | $0.02439 | $0.02439 |
| Sonnet 5 | $0.00975 | $0.00975 |
| Haiku 4.5 | $0.00488 | $0.00488 |
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.
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).
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.
- today Changed 303082913ba1
- yesterday Changed · +8 lines · +65 tokens per session abfce6c7122b
- 5d ago First seen · 285 lines · 4,812 tokens per session scan A 6d806981abba
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.
Other instructions, from other repositories
Muninn GEMINI.md
Gemini CLI instructions for wjohns989/Muninn, covering muninn mcp — sota+ development context, 🚀 sota+ development philosophy, 🛠 operational guidelines (always-on), 🏗 system architecture and 📂 project structure.
project-trucha AGENTS.md
Instructions for MaximilianoRodrigoSoria/project-trucha, a project described as: 🐟 Memoria persistente y local-first para agentes de código: indexa un codebase y lo recupera con búsqueda híbrida (léxica + vectorial) sobre SQLite/FTS5, sin infraestructura pesada. En etapa de decisión técnica.
seeklink AGENTS.md
Instructions for simonsysun/seeklink, covering project conventions for ai coding agents, core model, start of session, current focus and handoff (yyyy-mm-dd, agent, branch).
seeklink CLAUDE.md
Instructions for simonsysun/seeklink, covering claude code only and claude-triggered codex second review.
remnic AGENTS.md
AGENTS.md instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.