Borrowing it
Nothing to install: this file belongs to xyzzylabs/tc39-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/xyzzylabs/tc39-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/xyzzylabs/tc39-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/xyzzylabs/tc39-mcp/agents-md)<a href="https://agentmods.dev/instructions/xyzzylabs/tc39-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/xyzzylabs/tc39-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/xyzzylabs/tc39-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/xyzzylabs/tc39-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 | $0.00838 | $0.00838 |
| Opus 5 | $0.00419 | $0.00419 |
| Sonnet 5 | $0.00168 | $0.00168 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
tc39-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 8d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project rules for AI agents
This file follows the cross-tool AGENTS.md
convention. Tool-specific alias files (CLAUDE.md, etc.) import
this file via @AGENTS.md so every agent reads the same rules
with no drift.
What tc39-mcp is
A general-purpose, public MCP server for the TC39 specs (ECMA-262 + ECMA-402). It exposes structured clauses, AOID-aware search, in+out cross-references, edition diffs, git history, test262 search, and proposal lookup over the Model Context Protocol — locally over stdio or hosted as a Cloudflare Worker over HTTP. The data is SHA-pinned and auto-refreshes every ~4 hours from the upstream tc39/* mains.
The server is the product. Tools, dependencies, and documentation should read as if written for any reader interested in the TC39 specs, not for one specific downstream consumer.
Hard rules
-
The tool surface stays narrow. Read-only, deterministic, no execution, no auth, no writes. New tools land only if they expose structured spec data and meet that contract — see
CONTRIBUTING.md§ "What kinds of changes are welcome". -
No subprocess fallbacks for hosted-incompatible paths. Anything that can't run behind a Cloudflare Worker (shell-out, network call, filesystem write) doesn't belong in the tool surface. The only subprocess in the whole server is
spec.history'sgit logagainst a vendored checkout; nothing else. -
Comments and docs describe the code, not a downstream workflow. Anything that would only make sense to someone familiar with a specific consumer of this server gets rewritten to describe the general behavior instead.
-
Commit messages, PR descriptions, and issue titles are part of the project's public surface. Same standard as code comments — describe what changed and why in general terms.
Code conventions
- TypeScript everywhere. Strict mode. Zod for input schemas. JSDoc
on every exported interface field — the
/toolspage is generated from these. - Source of truth for tool docs lives next to the schema. The
generated
docs/tools.mdpage is rebuilt bysrc/docs/build_api_reference.tson everynpm run docs:data; don't hand-edit it. - Co-locate examples with the schema as
<name>Examplesarrays — the generator picks them up automatically. - Tests live next to source as
*.test.ts. Worker tests underworker/src/**.vitest runruns both. - Generated artifacts (
docs/snapshots.md,docs/changelog.md) are gitignored.docs/tools.mdis tracked so a fresh clone or GitHub browser sees the full reference without a build step.
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.
- 8d ago First seen · 83 lines · 838 tokens per session scan A ad7b414c04eb
tc39-mcp AGENTS.md is an instructions file published in the GitHub repository xyzzylabs/tc39-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 838 tokens to every session, about $0.0042 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).
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).
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.
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.