Borrowing it
Nothing to install: this file belongs to viant/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/viant/mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/viant/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/viant/mcp/agents-md)<a href="https://agentmods.dev/instructions/viant/mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/viant/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/viant/mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/viant/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 | $0.00298 | $0.00298 |
| Opus 5.5 | $0.00119 | $0.00119 |
| Sonnet 5.5 | $0.00060 | $0.00060 |
| Haiku 4.5 | $0.00030 | $0.00030 |
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 yesterday.
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
Project instructions
Capability reuse and explicit user approval
- Before adding any feature or mechanism, inspect the owning framework's existing APIs, configuration, documentation, implementation, tests, and callers at the exact version used by the application. Prove the relevant native behavior with an executable example before proposing an alternative.
- Trace the existing path across layers and identify its owner. Reuse that path; remove demonstrated duplication instead of adding parallel wrappers, adapters, fallback paths, caches, validation, permission checks, or configuration switches.
- Before implementing a new feature or framework extension, consult the user with the existing options, evidence of the remaining gap, the smallest proposed change and owning layer, and compatibility implications. Obtain explicit approval of that approach first. A request to fix a regression is not approval to invent a new mechanism. Agent or reviewer recommendations do not substitute for user approval.
- Keep validation, strict/lenient argument handling, authorization and contract enforcement in the framework or producer that already owns them. Do not silently replace native lenient behavior with stricter application, host, proxy or UI rejection.
- Passing tests does not justify a redundant feature. Preserve existing contracts and add regressions through the real native path. Do not introduce a new API, flag, gate, compatibility layer or workaround solely to make a test pass.
- Carry these requirements into delegated work. When the user has already approved the exact approach, continue within that authorization; ask again only if the proposed approach or scope changes.
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.
- yesterday First seen · 12 lines · 298 tokens per session scan A 3f91977441d7
mcp AGENTS.md is an instructions file published in the GitHub repository viant/mcp (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 298 tokens to every session, about $0.0012 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 2026-11-08.
mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp AGENTS.mdviant/mcp | Instructions file | 5 | yesterday | Apache-2.0 | A | 298 | 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 | yesterday | 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 ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |