Borrowing it
Nothing to install: this file belongs to Nuruvala/grok-build-to-claude. 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/Nuruvala/grok-build-to-claude/main/CLAUDE.mdgit clone --depth 1 https://github.com/Nuruvala/grok-build-to-claudeWrote 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/nuruvala/grok-build-to-claude/claude-md)<a href="https://agentmods.dev/instructions/nuruvala/grok-build-to-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/nuruvala/grok-build-to-claude/claude-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/nuruvala/grok-build-to-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/nuruvala/grok-build-to-claude/claude-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 | $0.10886 | $0.10886 |
| Opus 5 | $0.05443 | $0.05443 |
| Sonnet 5 | $0.02177 | $0.02177 |
| Haiku 4.5 | $0.01089 | $0.01089 |
Grade A, and why
grok-build-to-claude CLAUDE.md scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
stream did. The same run first tried `curl` through `run_terminal_command`, took our `--deny` How it starts
The opening of the file, as written. The whole thing — 663 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code when working in this repository.
Overview
This repo builds grok-build-mcp-server — an MCP (Model Context Protocol) stdio server that
exposes the Grok Build CLI (grok) as tools callable from Claude Code, Cursor, VS
Code, and any other MCP client.
Claude Code ──stdio/MCP──▶ grok-build-mcp-server ──spawn──▶ grok CLI ──▶ xAI API
The server is a thin, well-typed process wrapper. It does not reimplement agent logic, does not
maintain its own conversation state beyond a job registry, and does not talk to the xAI API
directly. All intelligence lives in the grok CLI; our job is faithful argument construction,
robust process supervision, and clean MCP-shaped output.
The repo is intended to be published publicly and released to npm.
Why this exists
Driving out of a real workflow gap: when Codex usage runs out and work shifts to Grok Build via the
bundled /grok-build:* plugin commands, the handoff is unreliable — responses, run monitoring, and
session handling are all hit-and-miss. The plugin is prior art, not a target to match. Reliability
is the product. Every failure mode below is a specific thing this server must not reproduce.
| Failure mode in the plugin | Where | What we do instead |
|---|---|---|
Parses model output by scraping prose — tries JSON.parse, then a ```json fence, then slicing between the first { and last } |
lib/grok.mjs parseStructuredOutput() |
--output-format json; the result object is read from a documented field, never recovered from prose |
Defaults to --output-format plain, so structured fields must be reconstructed |
lib/grok.mjs buildHeadlessArgs() |
json or streaming-json always; plain is not an internal code path |
Invents its own crypto.randomUUID() session id, passes it as --session-id, and reports it as the run's session — including on paths where Grok never recorded it |
lib/grok.mjs runHeadlessAgent() |
Report the sessionId Grok returns. Reconcile against grok sessions — the CLI's own session store is the source of truth |
Unbounded output accumulation (stdout += chunk) with no cap |
lib/grok.mjs runHeadlessAgent() |
10 MB cap per stream with an explicit truncation marker |
| No wall-clock timeout and no kill path in the headless runner | lib/grok.mjs runHeadlessAgent() |
GROK_MCP_TIMEOUT_MS, SIGTERM then SIGKILL against the process group |
child.on("error") rejects and discards everything buffered so far |
lib/grok.mjs runHeadlessAgent() |
Partial output is always returned alongside the error |
Progress is two coarse phase strings — starting, then finalizing. Blind for the entire run |
lib/grok.mjs emitProgress() calls |
Parse streaming-json and forward per-event notifications/progress |
Calls grok import, a subcommand that does not exist in 1.0.0 |
lib/grok.mjs runImport() |
Not built. See "Known drift" below |
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.
- 11d ago First seen · 663 lines · 10,886 tokens per session scan A bab0557b0d6f
grok-build-to-claude CLAUDE.md is an instructions file published in the GitHub repository Nuruvala/grok-build-to-claude (0 stars, last pushed 13d ago), licensed MIT. It adds 10,886 tokens to every session, about $0.0544 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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).