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/zcaceres/builtwith-api/claude-mdgit clone --depth 1 https://github.com/zcaceres/builtwith-apiWrote 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/zcaceres/builtwith-api/claude-md)<a href="https://agentmods.dev/instructions/zcaceres/builtwith-api/claude-md"><img src="https://agentmods.dev/badge/instructions/zcaceres/builtwith-api/claude-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 | $0.00713 | $0.00713 |
| Opus 5 | $0.00357 | $0.00357 |
| Sonnet 5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
builtwith-api CLAUDE.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 4d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — builtwith-api
Project overview
Bun workspace monorepo for the BuiltWith API suite. Two npm packages:
builtwith-api— TypeScript SDK + CLI. All 13 API endpoints. Depends only onzod.builtwith-mcp— MCP server for Claude Desktop, Cursor, etc. Depends onbuiltwith-api+@modelcontextprotocol/sdk.
Tech stack
- Runtime: Bun (build, test, compile, workspaces)
- Language: TypeScript (strict mode, ESM-only)
- Validation: Zod v4 (
zod/v4import path) - Linting: Biome
- Docs: VitePress + TypeDoc
Key conventions
- Schemas are the source of truth — all types are inferred from Zod schemas via
z.infer<>. Never duplicate types manually. - Response schemas use
z.strictObject()— this catches upstream API drift. If BuiltWith adds new fields, the schema parse will fail, signaling that the schema needs updating. - Input schemas also use
z.strictObject()— prevents typos in option names from being silently ignored. - Dual request functions —
request()for strict JSON parsing,requestSafe()for endpoints (lists, trends) that occasionally return malformed JSON. - Commands registry —
packages/builtwith-api/src/commands.tsdefines all 13 commands once; both CLI and MCP consume the same definitions. - Minimal dependencies —
builtwith-apidepends only onzod.builtwith-mcpadds@modelcontextprotocol/sdk.
Commands
bun run build # Build all packages
bun run test # Test all packages
bun run lint # Biome check
bun run lint:fix # Biome auto-fix
bun run docs:dev # Local docs dev server
File structure
packages/
builtwith-api/
src/
index.ts — createClient() factory, all 13 API methods
schemas.ts — Zod schemas for inputs + responses, BuiltWithClient interface
commands.ts — Command registry shared by CLI and MCP
params.ts — URL building, query string, boolean flag mapping
request.ts — HTTP request, API error detection + Zod validation
errors.ts — Error formatting (Zod + generic)
config.ts — Constants (response format enum)
cli.ts — CLI entry point
format.ts — Table formatter for --table CLI output
test/
*.test.ts — Unit + integration tests (Bun test runner)
builtwith-mcp/
src/
mcp.ts — MCP server entry point
test/
mcp.test.ts — MCP server tests
docs/ — VitePress docs site (deployed to builtwith.zach.dev)
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.
- 4d ago First seen · 67 lines · 713 tokens per session scan A b22b02d7fd42
builtwith-api CLAUDE.md is an instructions file published in the GitHub repository zcaceres/builtwith-api (22 stars, last pushed 1mo ago), licensed MIT. It adds 713 tokens to every session, about $0.0036 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 2026-08-30.
Other instructions, from other repositories
tray-api-ai-plugin AGENTS.md
Instructions for tray-tecnologia/tray-api-ai-plugin, covering tray api plugin, regras obrigatórias para toda sessão, autenticação, url e formato and rate limit.
tray-api-ai-plugin copilot-instructions.md
Instructions for tray-tecnologia/tray-api-ai-plugin, covering tray api plugin, regras obrigatórias para toda integração tray, autenticação oauth 2.0, formato de requisições and rate limit.
tray-api-ai-plugin CLAUDE.md
Instructions for tray-tecnologia/tray-api-ai-plugin, covering tray api plugin — contexto para claude, regras obrigatórias, bloco mandatory e lint de skills, validação local and busca em docs.
tray-api-ai-plugin GEMINI.md
Instructions for tray-tecnologia/tray-api-ai-plugin, covering tray api plugin — contexto para gemini cli, regras obrigatórias, bloco mandatory e lint de skills, validação local and busca em docs.
gortex CLAUDE.md
Claude Code instructions for zzet/gortex, covering gortex, build & test, codebase overview, discovery (read once, then keep using) and llm provider (powers ask and searchsymbols assist: modes).
agent-toolkit AGENTS.md
Instructions for ulises-jeremias/agent-toolkit, covering agents.md — ai agent contract, what this toolkit does, repository structure, operating rules and how to add a skill.