Borrowing it
Nothing to install: this file belongs to vantage-sh/vantage-mcp-server. 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/vantage-sh/vantage-mcp-server/main/AGENTS.mdgit clone --depth 1 https://github.com/vantage-sh/vantage-mcp-serverWrote 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/vantage-sh/vantage-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/vantage-sh/vantage-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/vantage-sh/vantage-mcp-server/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/vantage-sh/vantage-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/vantage-sh/vantage-mcp-server/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 | $0.01849 | $0.01849 |
| Opus 5.5 | $0.00740 | $0.00740 |
| Sonnet 5.5 | $0.00370 | $0.00370 |
| Haiku 4.5 | $0.00185 | $0.00185 |
Grade A, and why
vantage-mcp-server 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 9d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Working notes for agents in this repo. The README covers setup and deployment; this file lists the traps that are not obvious from a quick file scan.
This file is not a recipe. Step-by-step instructions live in the skills and subsystem READMEs linked below. Do not reconstruct conventions from neighboring files — much of the existing code predates current conventions.
Leave unrelated convention drift alone. Fixing it belongs in a separate PR.
How tools plug in
Every tool file's default export is a registerTool({...}) call (src/tools/structure/registerTool.ts). Tools become live by being imported — that is all src/tools/index.ts does. The index is generated by npm run generate-tools-index; test/tools/index.test.ts fails CI if it is stale.
New tools go under src/tools/<resource>/, not at the top level of src/tools/, and must ship with a matching unit test under test/ (testTool). Add import "./<verb>-<resource>"; to the resource's index.ts, then run npm run generate-tools-index. Never hand-edit src/tools/index.ts.
Also generated — never hand-edit: src/resources/index.ts (npm run generate-resources-index), worker-configuration.d.ts (npm run cf-typegen).
Useful examples to copy:
- Nested tool family:
src/tools/budgets/,src/tools/cost-reports/ - Another nested family with shared request typing:
src/tools/recommendation-views/ - Delete tool and 204 behavior:
src/tools/folders/delete-folder.ts
Invariants
These are easy to violate by copying a neighbor. The skills show the full patterns; this is the checklist.
- URL path tokens use
pathEncode. Any token interpolated into a Vantage API path goes throughpathEncodefrom@vantage-sh/vantage-client. Seefolders/delete-folder.ts,teams/get-team.ts. callVantageApireturns a discriminated union.{ ok: true, data }or{ ok: false, errors }. Checkresponse.okand throwMCPUserErrorwith the errors. Do not try/catch around the call —registerToolhandles translation.- 204 No Content is normalized in
src/shared.tsto{ ok: true, data: undefined }. Delete tools must not touchresponse.data. - Delete tools return
{ token: args.<resource>_token }. Confirms what was deleted without leaking anything. Seefolders/delete-folder.ts. MCPUserErrorconstructor takes a plain object.new MCPUserError({ errors: response.errors })for upstream failures;new MCPUserError({ errors: [{ message: "..." }] })for cross-field validation. Do not pass anError.- Vantage client types are the source of truth for request/response shape (
RequestBodyForPathAndMethod/ResponseBodyForPathAndMethodfrom@vantage-sh/vantage-client). When the zod-inferred type does not line up, cast at thecallVantageApisite — seerecommendation-views/create-recommendation-view.ts,cost-reports/create-cost-report.ts,cost-providers/get-cost-provider-accounts.ts.
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.
- 9d ago Changed · +15 lines · +510 tokens per session 5fe6d6d5c20b
- 10d ago Changed · -9 lines · -72 tokens per session ed0ade93c295
- 2mo ago First seen · 72 lines · 1,411 tokens per session scan A 481abcf18ce5
vantage-mcp-server AGENTS.md is an instructions file published in the GitHub repository vantage-sh/vantage-mcp-server (86 stars, last pushed 2d ago), licensed MIT. It adds 1,849 tokens to every session, about $0.0074 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 2026-08-30.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.