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/lxvault/mcp/agents-mdgit clone --depth 1 https://github.com/LXVault/mcpWhat 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 | $0.00906 | $0.00906 |
| Opus 5 | $0.00453 | $0.00453 |
| Sonnet 5 | $0.00181 | $0.00181 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Strict Rules:
- Agents must read
AGENTS.md,SKILLS.md, and allREADME.mdfiles located within the documented Agent Directories, and save their entire contents within memory. - Agents must ask for the user's approval before editing
AGENTS.mdorSKILLS.md. - Every agent-related directory (e.g.,
.agents/,.skills/,.tools/) must contain aREADME.mdfile that serves as the index for its contents. Do not index these files in the rootAGENTS.mdorSKILLS.md. - Never work directly on the
masterormainbranch. - Always verify if your current task aligns with the active branch. If it does not, create a new branch. Do not create a new branch if you are continuing existing work on the appropriate branch.
- When finishing work, you must also check the code security for any files that were modified and committed in the current branch.
- Code and comments must not contain dashes.
The root AGENTS.md and SKILLS.md files must remain universally applicable to the entire repository. If you conceptualize a new instruction, skill, tool, or any context-specific data that is not universally applicable, create it within the appropriate Agent Directory (such as .agents/, .skills/, .tools/, .personas/, etc.) instead.
Agent Directories
| Name | Description |
|---|---|
.tools/ |
Contains definitions, schemas, or scripts of tools the agents are permitted to use. |
.knowledge/ |
Domain-specific context, reference documents, or knowledge base for the agent. |
.personas/ |
Defines specific roles, personalities, or perspectives for agents to adopt. |
.ethics/ |
Safety bounds, ethical guidelines, and constraints to ensure responsible agent behavior. |
Suggesting New Content
While working, if you discover a useful idea, rule, or skill that could improve AGENTS.md or SKILLS.md, do not apply the changes immediately. Instead, upon finishing your current task, suggest the new additions to the user and allow them to decide whether to integrate them.
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 · 57 lines · 906 tokens per session scan A 55afa4483235
mcp AGENTS.md is an instructions file published in the GitHub repository LXVault/mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 906 tokens to every session, about $0.0045 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.