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/nambok/mentedb/claude-mdgit clone --depth 1 https://github.com/nambok/mentedbWrote 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/nambok/mentedb/claude-md)<a href="https://agentmods.dev/instructions/nambok/mentedb/claude-md"><img src="https://agentmods.dev/badge/instructions/nambok/mentedb/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 | $0.00997 | $0.00997 |
| Opus 5 | $0.00498 | $0.00498 |
| Sonnet 5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
mentedb 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 3d 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.
This is a copy
95% identical to mentedb copilot-instructions.md — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MenteDB Development Instructions
Project overview
MenteDB is a purpose built Rust database engine for AI agent memory. It includes custom storage (WAL, buffer pool, pages), HNSW vector indexing, CSR/CSC graph, a custom query language (MQL), context assembly with U curve attention layout, and 7 unique cognitive features (stream cognition, write time inference, trajectory tracking, phantom memories, interference detection, pain signals, speculative pre assembly).
Workspace structure
crates/
mentedb-core/ Core types, config, error, MVCC, multi agent
mentedb-storage/ Page manager, WAL, buffer pool, backup/restore
mentedb-index/ HNSW vector index, bitmap, temporal, salience
mentedb-graph/ CSR/CSC graph, traversal, belief propagation
mentedb-query/ MQL lexer, parser, planner
mentedb-context/ U curve attention layout, delta tracker, serializers
mentedb-cognitive/ Stream cognition, write inference, trajectory, phantoms, interference, pain, speculative
mentedb-consolidation/ Decay, archival, extraction, compression, GDPR forget
mentedb-embedding/ Provider trait, hash/HTTP providers, LRU cache
mentedb-server/ Axum REST API, JWT auth, rate limiting, WebSocket
mentedb/ Unified facade (MenteDb struct)
sdks/
python/ PyO3 bindings + pure Python client
typescript/ napi-rs bindings + TypeScript client
python/integrations/langchain/ LangChain memory, retriever, chat history
python/integrations/crewai/ CrewAI memory and tool adapter
The SDKs are excluded from the Cargo workspace and build independently.
Build, test, and lint
Always run these before committing:
cargo fmt --all
cargo clippy --workspace -- -D warnings
cargo test --workspace
The server binary is mentedb-server and runs on axum with JWT auth, rate limiting, and WebSocket support.
Key types
MemoryNode: The fundamental storage unit (id, content, memory_type, embedding, metadata, timestamps)MemoryEdge: Typed relationship between memories (caused, contradicts, relates_to, obsoletes, etc.)MenteDb: The unified facade that coordinates all subsystemsMenteConfig: Top level config with sub configs for every subsystemMenteError/MenteResult<T>: Error handling throughout
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.
- 3d ago First seen · 85 lines · 997 tokens per session scan A d547ac173c6b
mentedb CLAUDE.md is an instructions file published in the GitHub repository nambok/mentedb (116 stars, last pushed 8d ago), licensed Apache-2.0. It adds 997 tokens to every session, about $0.0050 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to mentedb copilot-instructions.md, differing in 2 lines, and is treated as a copy.
Other instructions, from other repositories
bitterbot-desktop AGENTS.md
AGENTS.md instructions for Bitterbot-AI/bitterbot-desktop, covering bitterbot — repository guidelines, what is bitterbot?, what makes bitterbot different, 1. memory system (src/memory/) and 2. dream engine (src/memory/dream-engine.ts).
prism-coder GEMINI.md
Gemini CLI instructions for dcostenco/prism-coder: See the Synalux engineering standards doc for the full protocol. This file inherits those standards. Additional Prism-specific rules.
linggen-memory CLAUDE.md
Claude Code instructions for linggen/linggen-memory, covering claude code instructions, purpose, status, scope and working rules.
neurodivergent-memory copilot-instructions.md
Instructions for jmeyer1980/neurodivergent-memory, covering neurodivergent-memory — agent bootstrap instructions, what this server is, canonical tag schema, districts and available mcp tools (quick reference).
agidb CLAUDE.md
Instructions for rohansx/agidb, covering agidb — claude code instructions, naming, before changing anything, agent skills and issue tracker.
leptin AGENTS.md
AGENTS.md instructions for lionellau/leptin, covering leptin — for the agent, when to install yourself, install yourself (one block, unattended), how to use it (every session) and what to tell your human.