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/owrede/vault-memory/claude-mdgit clone --depth 1 https://github.com/owrede/vault-memoryWrote 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/owrede/vault-memory/claude-md)<a href="https://agentmods.dev/instructions/owrede/vault-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/owrede/vault-memory/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 | $0.05897 | $0.05897 |
| Opus 5 | $0.02949 | $0.02949 |
| Sonnet 5 | $0.01179 | $0.01179 |
| Haiku 4.5 | $0.00590 | $0.00590 |
Grade A, and why
vault-memory 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.
How it starts
The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project
vault-memory — Agentic Knowledge Layer (v2)
vault-memory is an MIT-licensed, local-first MCP server that exposes Obsidian vaults to MCP-aware agents (Claude Code, Claude desktop, ChatGPT Custom Connectors, generic MCP clients) as a set of tools for search, graph navigation, frontmatter queries, and atomic writes. Today (v1.0.0) it is a strong retrieval substrate — hybrid search (semantic + BM25 + RRF, optional cross-encoder rerank), 23 MCP tools, live indexing, multi-vault, hash-protected writes. The v2 project evolves it from "Layer 0 retrieval" into a full agentic knowledge layer: memory namespace with provenance, document-tree retrieval, authority/staleness signals, graph-as-retrieval, a compiled-brief layer that beats the "agents rediscover 85% of context every run" failure mode, and user-defined task contracts that any MCP-aware agent can discover and instantiate.
Core Value: Local-first, source-agnostic-ready, agentic knowledge layer over your Obsidian notes
— with the memory namespace as a non-negotiable safety invariant. Agents never write
silently into user notes; every agent-authored document carries provenance properties
and lives in a labeled MemorySink.
Using vault-memory as an agent (task contracts)
This block guides an agent that operates vault-memory as an MCP server for a user — not an agent editing this codebase. It is the discoverability bridge for the contract tools, mirrored by the
use-contractsskill (skills/use-contracts/).
When a user asks for an outcome that a task contract already produces — a meeting-prep brief, a project status, a code-review brief, or any "compile / pull together / summarize X from my notes" request — prefer running the matching contract over assembling the answer ad hoc. Contracts are the user's saved, repeatable recipes; they gather the right notes and compile a brief into the memory sink with provenance.
The flow (the use-contracts skill spells it out step by step):
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 · 327 lines · 5,897 tokens per session scan A cd298585a3d1
vault-memory CLAUDE.md is an instructions file published in the GitHub repository owrede/vault-memory (0 stars, last pushed 25d ago), licensed MIT. It adds 5,897 tokens to every session, about $0.0295 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.
Other instructions, from other repositories
cognirepo CLAUDE.md
Instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).
openexp CLAUDE.md
Instructions for anthroos/openexp, covering openexp — development instructions, memory protocol (mandatory), before starting any task, after completing a task and when the user shares context.