Borrowing it
Nothing to install: this file belongs to LXVault/mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/LXVault/mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/LXVault/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/lxvault/mcp/agents-md)<a href="https://agentmods.dev/instructions/lxvault/mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/lxvault/mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/lxvault/mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/lxvault/mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02220 | $0.02220 |
| Opus 5.5 | $0.00888 | $0.00888 |
| Sonnet 5.5 | $0.00444 | $0.00444 |
| Haiku 4.5 | $0.00222 | $0.00222 |
Grade A, and why
agents-entry-point 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 2mo 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
This repository is mcp-rag-mcp-server, a Model Context Protocol server that exposes the
MCP RAG knowledge base to MCP compatible clients such as Claude Desktop and IDE
assistants. It speaks JSON-RPC over stdio and holds no state and no logic of its own:
every tool is a thin call to the Express backend in LXVault/server-expressjs, carrying a
per project access token so the backend can attribute each action to the user who issued
that token.
Shared Instruction Set
The conventions this repository follows, branching, commits, pull requests, task
workflow, the creators, live in the shared instruction set served by the
lxagents-agents-base MCP server. This repository carries only what is its
own. Resolve the shared set before doing any work:
- If the
lxagents-agents-baseconnector is available in this session, that is the shared set. Refer to it as{shared}; its files are addressed asagents://{folder}/{file}.md. - Resolving is not loading. Do not pull any convention at session start. The Shared instruction tools block below declares which tools this repository uses and the trigger for each; call one when its trigger fires, and not before.
- Where the client exposes no tools, the same conventions are read as
agents://{folder}/{file}.mdresources, on the same triggers.list_shared_agents_instruction, oragents://manifest.json, answers "what exists?" in one call. Do not bulk-read the set. - If the connector is not available, say so plainly and continue with this repository's local instruction set only. Do not reconstruct the missing rules from memory, and do not clone or copy them into this repository.
The declaration block is required. A repository without one has no routing table,
so nothing fires and the omission looks exactly like a session in which no convention
happened to apply. It names the four mandatory tools at minimum, task_workflow,
branch_strategy, commit_strategy, discovery_protocol, and stamps the set version
adopted. Shape: {shared}/prompts/agents-setup.md. Keeping it current when this set
moves: {shared}/prompts/agents-update.md, on request.
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.
- 2mo ago Changed · +135 lines · +1,314 tokens per session 927912c646ef
- 2mo ago First seen · 57 lines · 906 tokens per session scan A 55afa4483235
agents-entry-point is an instructions file published in the GitHub repository LXVault/mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,220 tokens to every session, about $0.0089 per session on Opus 5.5. 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.
agents-entry-point compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agents-entry-pointLXVault/mcp | Instructions file | 0 | 1mo ago | MIT | A | 2,220 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |