Borrowing it
Nothing to install: this file belongs to 1mcp-app/agent. 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/1mcp-app/agent/main/AGENTS.mdgit clone --depth 1 https://github.com/1mcp-app/agentWrote 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/1mcp-app/agent/agents-md)<a href="https://agentmods.dev/instructions/1mcp-app/agent/agents-md"><img src="https://agentmods.dev/badge/instructions/1mcp-app/agent/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/1mcp-app/agent/agents-md"><img src="https://agentmods.dev/badge/instructions/1mcp-app/agent/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 | $0.01177 | $0.01177 |
| Opus 5.5 | $0.00471 | $0.00471 |
| Sonnet 5.5 | $0.00235 | $0.00235 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
agent 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 today.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
1MCP aggregates MCP servers behind one endpoint. Repository: 1mcp-app/agent; public docs: https://docs.1mcp.app.
Start with the relevant context
- Before exploring a domain, read docs/agents/domain.md, use the vocabulary in
GLOSSARY.mdwhen present, and consult the relevant decisions indocs/adr/. - Before editing anything under
docs/, read docs/AGENTS.md. It defines public URL preservation, bilingual changes, development-note placement, and site verification. - For issue or PRD work, read docs/agents/issue-tracker.md; for triage labels, read docs/agents/triage-labels.md.
- For setup and development workflows, consult the development guide. Use
.node-versionand thepackageManagerfield inpackage.jsonfor toolchain versions;package.jsonscripts and.github/workflows/define executable checks.
Scope and completion
- Preserve existing staged and unstaged changes. Carry the authorized task through implementation, verification, and requested delivery; keep commits, pushes, PR creation, merge, and deployment within the user's authorization.
- Resolve routine, reversible choices from current source and repository conventions. Ask when an unresolved decision materially changes behavior, compatibility, scope, or external effects; continue independent authorized work while it is unresolved.
- Report the changed behavior, checks actually run, and unresolved failures or coverage gaps. Local validation, hosted CI, and deployment are separate results. “Verify” and “confirm” require evidence, not a human approval checkpoint unless explicitly requested.
Development and verification
Run commands from the repository root. Install dependencies with pnpm install. pnpm dev starts the development watcher and creates .env from .env.example if absent; preserve any existing .env.
| Task | Command / rule |
|---|---|
| Build | pnpm build |
| Focused source tests | pnpm test:unit <path/to/file.test.ts>; source tests are co-located |
| Admin UI | pnpm test:admin and pnpm typecheck:admin |
| Required before committing | pnpm check |
| Documentation changes | pnpm docs:build |
| Process, HTTP, browser, or protocol changes | Build first, then choose the relevant E2E lane from test/e2e/README.md |
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.
- today Changed · +44 tokens per session 1089ac1110cf
- yesterday Changed · -129 lines · -629 tokens per session b470a83227c2
- 3d ago Changed c8e7b43297e4
- 21d ago First seen · 187 lines · 1,762 tokens per session scan A 9dfb19d32abd
agent AGENTS.md is an instructions file published in the GitHub repository 1mcp-app/agent (524 stars, last pushed today), licensed Apache-2.0. It adds 1,177 tokens to every session, about $0.0047 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 2026-10-05.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.