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/cubicecho/graphql-mcp/agents-mdgit clone --depth 1 https://github.com/cubicecho/graphql-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/cubicecho/graphql-mcp/agents-md)<a href="https://agentmods.dev/instructions/cubicecho/graphql-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/cubicecho/graphql-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.10555 | $0.10555 |
| Opus 5 | $0.05278 | $0.05278 |
| Sonnet 5 | $0.02111 | $0.02111 |
| Haiku 4.5 | $0.01056 | $0.01056 |
Grade A, and why
graphql-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.
How it starts
The opening of the file, as written. The whole thing — 609 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project
@cubicecho/graphql-mcp — middleware that turns a GraphQL schema into a
Model Context Protocol server. Each
Query/Mutation root field is projected into an MCP tool, described from
the SDL (field and argument descriptions, types) so an AI can discover and call
your API. It is designed to run side-by-side with your GraphQL server: mount
the returned HTTP handler on a route in the same app, or run it as its own
process and forward to a remote GraphQL endpoint.
Stack
- Language: TypeScript 5.7+, strict mode, ESM only, "erasable syntax only" (no enums/namespaces/parameter-properties) so the source runs unbuilt under Node's type stripping.
- Runtime/build: Source uses
.tsimport specifiers. Run it directly withnode --experimental-strip-types;tsc(withrewriteRelativeImportExtensions) rewrites the specifiers to.jsand emitsdist/. Requires Node ≥ 22 and TypeScript ≥ 5.7. - Tests: Node's built-in test runner (
node --test) with type stripping — no test framework dependency. Test files aresrc/**/*.test.ts. - Formatting/linting: Biome (
npm run check). - Dependencies:
@graphql-tools/schema(schema merging for theextendoption) is the only runtime dependency.@modelcontextprotocol/sdk(>=1.12),graphql(>=16) andzod(^3.25 || ^4.0) are peer deps — zod because the SDK validates against the caller's copy, and a second one in our own tree makesinstanceofchecks fail across the boundary. Express is not a dependency — the HTTP handler is framework-agnostic.createFetchHandlerneeds SDK ≥ 1.25 and loads that transport lazily so the floor stays at 1.12 for everyone else. - Guiding constraint: avoid adding libraries unless writing it ourselves
isn't worth the effort (e.g. the GraphQL→Zod mapping is hand-written). The
scalarsoption is a plainRecord<string, AnyZodType>for the same reason — it's structurally identical to what generators emit (e.g.defaultScalarMapfrom@vantreeseba/graphql-zod), so interop needs no adapter or dependency.
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 Changed · +395 lines · +7,302 tokens per session 8fd50d0f3c41
- 4d ago First seen · 214 lines · 3,253 tokens per session scan A e4a8006fcfa7
graphql-mcp AGENTS.md is an instructions file published in the GitHub repository cubicecho/graphql-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 10,555 tokens to every session, about $0.0528 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
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.
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.
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.
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).