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/maxrotemberg04-spec/rag-vault/agents-mdgit clone --depth 1 https://github.com/maxrotemberg04-spec/rag-vaultWrote 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/maxrotemberg04-spec/rag-vault/agents-md)<a href="https://agentmods.dev/instructions/maxrotemberg04-spec/rag-vault/agents-md"><img src="https://agentmods.dev/badge/instructions/maxrotemberg04-spec/rag-vault/agents-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 | $0.00260 | $0.00260 |
| Opus 5 | $0.00130 | $0.00130 |
| Sonnet 5 | $0.00052 | $0.00052 |
| Haiku 4.5 | $0.00026 | $0.00026 |
Grade A, and why
rag-vault AGENTS.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 5d 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.
What it actually says
rag-vault — agent instructions
Local-first RAG over Max's Obsidian vault — ask the second brain questions in the terminal, get grounded answers with citations that deep-link back into Obsidian. Retrieval is hand-rolled (BM25 + embeddings + reciprocal rank fusion), and the engine doubles as an MCP server so local agents can search the notes as a tool.
Public portfolio repo — this code is part of Max's pitch; keep it interview-clean. Python 3.12. Tests: pytest -q (same as CI).
Hard rules
- Commits are 100% Max. Never add AI co-author trailers or AI attribution to commits, code comments, or docs.
- Evidence before "done" — run the tests and show the output.
- No secrets in git;
.envstays local — and never commit real vault content; fixtures/demo notes only. - Teach while doing — Max is learning; explain the why in plain terms as you work.
- Cross-model review before merge on non-trivial changes — whichever model wrote it, the other reviews.
Keep diffs small and readable — every line in this repo should be explainable in an interview.
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.
- 5d ago First seen · 16 lines · 260 tokens per session scan A 5ff11938324a
rag-vault AGENTS.md is an instructions file published in the GitHub repository maxrotemberg04-spec/rag-vault (0 stars, last pushed 1mo ago), licensed MIT. It adds 260 tokens to every session, about $0.0013 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
VelesDB CLAUDE.md
Claude Code instructions for cyberlife-coder/VelesDB: Local-first unified database (Vector + Graph + ColumnStore) under VelesQL. Rust workspace, single 14 MB binary.
personal-notes-assistant CLAUDE.md
Instructions for coeusyk/personal-notes-assistant, covering personal-notes-assistant, architecture, adding a tool, milvus notes (non-obvious, bit people twice already) and running / testing locally.
grounding-ai CLAUDE.md
Claude Code instructions for andyliszewski/grounding-ai, covering claude.md, critical requirements, python version, embedding generation is mandatory and after ingestion, update embeddings for affected agents.
obsidian-rag-mcp CLAUDE.md
Claude Code instructions for danielscholl/obsidian-rag-mcp, covering claude.md — project context for ai assistants, project overview, quick commands, install and run all tests.
RAGLight CLAUDE.md
Claude Code instructions for Bessouat40/RAGLight, covering claude.md, commands, install dependencies, run all tests and run a single test module.
OpenDocuments AGENTS.md
Instructions for joungminsung/OpenDocuments, covering agents.md, project overview, monorepo structure, common commands and 특정 패키지만.