What is grok-skill CLAUDE.md?

A project instruction file for grok-skill, a Claude Code skill that searches X/Twitter through Grok 4. It documents the repository, its Bun TypeScript script, command options, and required API key.

Use it when developing grok-skill, including its command-line parsing, search filters, Bun runtime, or OpenRouter connection.

It tells coding agents how the project is organized and how to run or modify the search skill without overlooking its configuration requirements.

How mikedemarais/grok-skill configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mikedemarais/grok-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/mikedemarais/grok-skill/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mikedemarais/grok-skill

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mikedemarais/grok-skill/claude-md.svg)](https://agentmods.dev/instructions/mikedemarais/grok-skill/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/mikedemarais/grok-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/mikedemarais/grok-skill/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 3,500 This file is loaded in full into every session.

When invoked 3,500 The same file — it is already loaded in full.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.03500	$0.03500
Opus 5	$0.01750	$0.01750
Sonnet 5	$0.00700	$0.00700
Haiku 4.5	$0.00350	$0.00350

Measured 8d ago against content hash e0463b5f8f53, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

grok-skill CLAUDE.md scanned grade B 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 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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

ls -la ~/.claude/skills/grok-skill

CLAUDE.md · 479 lines

How it starts

The opening of the file, as written. The whole thing — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — grok-skill

Guidelines for Claude Code when working on the grok-skill repository.

Repository Overview

Item	Value
Purpose	Claude Code Skill for X/Twitter search via Grok 4 (OpenRouter)
Location	`~/.claude/skills/grok-skill/` (user skill directory)
Dev Repo	`~/git/grok-skill/` (this repo for development)
Primary Script	`scripts/grok.ts` (Bun TypeScript)
API Provider	OpenRouter (`x-ai/grok-4` model)
API Key Source	Environment variable `$OPENROUTER_API_KEY`
Runtime	Bun

File Structure

grok-skill/
├── .gitignore         # Protects secrets (.env, .env.*)
├── SKILL.md           # Skill definition for Claude Code
├── README.md          # User documentation
├── CLAUDE.md          # This file (development guidelines)
└── scripts/
    └── grok.ts        # Main executable TypeScript script

Architecture

Module Responsibilities

CLI Parsing (parseArgs):

Multi-value flag collection for --include / --exclude
Validates --mode (on|off|auto)
Validates numeric bounds for --max, --min-faves, --min-views
Enforces mutual exclusivity between include/exclude

Normalization:

Strips '@' prefix from handles
Lowercases and deduplicates handles
Caps handle lists at 10
Validates dates to real calendar values (rejects 2025-02-30)
Clamps --max to [1..50] range

API Client (fetchWithRetry):

30-second timeout via AbortController
Exponential backoff retries (up to 3 attempts)
Honors Retry-After header for rate limits
Retries on 408/429/5xx errors
Logs request-id when available

Request Building:

Constructs extra_body.search_parameters with:
- mode, return_citations, max_search_results
- from_date, to_date (ISO format)
- sources array with X-specific filters
Sets temperature: 0.2, max_tokens: 1200

Response Handling:

Primary: choices[0].message.content
Fallback: choices[0].delta.content
Citations: Checks citations, choices[0].message.citations, extra.citations
Fallback: Extracts https://x.com/* and https://twitter.com/* URLs from text

Read the full file on GitHub · 479 lines

Changes

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 · 479 lines · 3,500 tokens per session scan B e0463b5f8f53

Subscribe to this mod's changes

grok-skill CLAUDE.md is an instructions file published in the GitHub repository mikedemarais/grok-skill (18 stars, last pushed 10mo ago), licensed MIT. It adds 3,500 tokens to every session, about $0.0175 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code claude-code-skills claude-skills grok openrouter xai

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

grok-skill: Instructions file for Claude Code