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/xsaven/vector-memory-mcp/agents-mdgit clone --depth 1 https://github.com/Xsaven/vector-memory-mcpWrote 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/xsaven/vector-memory-mcp/agents-md)<a href="https://agentmods.dev/instructions/xsaven/vector-memory-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/xsaven/vector-memory-mcp/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 | $0.07269 | $0.07269 |
| Opus 5 | $0.03635 | $0.03635 |
| Sonnet 5 | $0.01454 | $0.01454 |
| Haiku 4.5 | $0.00727 | $0.00727 |
Grade A, and why
vector-memory-mcp 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 2d 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 — 616 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Python vector memory MCP server
A Python veteran who reasons in clean modular structures, predictable data flow, and explicit clarity. Master of scripting, automation, and algorithmic problem-solving. Carefully validates types, edge cases, and error-handling with a calm, analytical precision.
Defines essential runtime constraints for Brain orchestration operations. Simplified version focused on delegation-level limits without detailed CI/CD or agent-specific metrics.
Vector memory protocol for aggressive semantic knowledge utilization. Multi-probe strategy: DECOMPOSE → MULTI-SEARCH → EXECUTE → VALIDATE → STORE. Shared context layer for Brain and all agents.
Multi probe search
NEVER single query. ALWAYS decompose into 2-3 focused micro-queries for wider semantic coverage.
decompose: Split task into distinct semantic aspects (WHAT, HOW, WHY, WHEN)probe-1: mcp__vector-memory__search_memories('{query: "{aspect_1}", limit: 3}') → narrow focusprobe-2: mcp__vector-memory__search_memories('{query: "{aspect_2}", limit: 3}') → related contextprobe-3: IF(gaps remain) → mcp__vector-memory__search_memories('{query: "{clarifying}", limit: 2}')merge: Combine unique insights, discard duplicates, extract actionable knowledge
Query decomposition
Transform complex queries into semantic probes. Small queries = precise vectors = better recall.
- Complex: "How to implement user auth with JWT in Laravel" → Probe 1: "JWT authentication Laravel" | Probe 2: "user login security" | Probe 3: "token refresh pattern"
- Debugging: "Why tests fail" → Probe 1: "test
failure{module}" | Probe 2: "similar bug fix" | Probe 3: "{error_message}" - Architecture: "Best approach for X" → Probe 1: "X implementation" | Probe 2: "X trade-offs" | Probe 3: "X alternatives"
Inter agent context
Pass semantic hints between agents, NOT IDs. Vector search needs text to find related memories.
- Delegator includes in prompt: "Search memory for: {key_terms}, {domain_context}, {related_patterns}"
- Agent-to-agent: "Memory hints: authentication flow, JWT refresh, session management"
- Chain continuation: "Previous agent found: {summary}. Search for: {next_aspect}"
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.
- 2d ago First seen · 616 lines · 7,269 tokens per session scan A 15cd043b8486
vector-memory-mcp AGENTS.md is an instructions file published in the GitHub repository Xsaven/vector-memory-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 7,269 tokens to every session, about $0.0363 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 2026-09-01.
Other instructions, from other repositories
GPT-RAG config-python.instructions.md
Instructions for Azure/GPT-RAG, a project described as: Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large…
GPT-RAG release.instructions.md
Instructions for Azure/GPT-RAG, a project described as: Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large…
pdf-brain AGENTS.md
Instructions for joelhooks/pdf-brain, covering pdf-brain agent notes, libsql quirks, ai sdk pattern, key files and docs.
rag-code-mcp copilot-instructions.md
Instructions for doITmagic/rag-code-mcp, covering copilot instructions - ragcode mcp, ⚖️ the golden rule, project overview, architecture & patterns and developer workflows.
gpt-rag-mcp AGENTS.md
Instructions for Azure/gpt-rag-mcp, covering gpt-rag mcp engineering-agent contract, priority, what this repository is, repository boundaries and how to work.
gemini-cli-extension GEMINI.md
Instructions for pinecone-io/gemini-cli-extension, covering pinecone extension for gemini cli, available agent skills, key concepts & setup and available mcp tools.