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/shafthq/shaft_mcp/copilot-instructionsgit clone --depth 1 https://github.com/ShaftHQ/SHAFT_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/shafthq/shaft_mcp/copilot-instructions)<a href="https://agentmods.dev/instructions/shafthq/shaft_mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/shafthq/shaft_mcp/copilot-instructions.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 5.1 | $0.03288 | $0.03288 |
| Opus 5 | $0.01644 | $0.01644 |
| Sonnet 5 | $0.00658 | $0.00658 |
| Haiku 4.5 | $0.00329 | $0.00329 |
Grade A, and why
SHAFT_MCP copilot-instructions.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 5d 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.
curl -N -H "Accept: text/event-stream" http://localhost:8081/mcp How it starts
The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SHAFT MCP - GitHub Copilot Instructions
Project Overview
SHAFT MCP is a Model Context Protocol (MCP) server that enables Claude Desktop to perform web automation tasks using the SHAFT Engine (a Selenium-based test automation framework). The project is built with:
- Language: Java 25 (Temurin 25 LTS or newer)
- Framework: Spring Boot 4.0.5 with Spring AI 1.1.4
- Build Tool: Maven 3.x
- Testing Framework: JUnit Jupiter (JUnit 5) via TestNG-compatible surefire profile
- Web Automation: SHAFT Engine 10.2.20260422 (Selenium-based)
- Distribution: JAR file, Docker image, Maven Central
Technology Stack
- Spring Boot for application framework
- Spring AI for MCP server implementation (STDIO and HTTP/SSE transports)
- SHAFT Engine for browser automation (Selenium WebDriver)
- Allure for test reporting
- SLF4J for logging
Build & Test Commands
Build the Project
mvn clean package -DskipTests -Dgpg.skip
This creates the JAR file in target/SHAFT_MCP-10.2.20260422.jar
Run Tests (requires Selenium Grid)
# Pre-create the properties directory to prevent SHAFT Engine IOException
mkdir -p src/main/resources/properties
# Point to a running Selenium Grid
REMOTE_DRIVER_ADDRESS=http://localhost:4444/wd/hub mvn clean test -Pjunit
Tests must be run with the junit Maven profile (-Pjunit). The CI integration test
workflow (integration-test.yml) spins up a selenium/standalone-chrome:latest container
on port 4444 before running the tests.
IMPORTANT — run tests before any code merge: Tests must be executed and confirmed passing before merging code changes. If tests fail, iterate to fix the problem and re-run. Keep iterating until all tests pass.
Full Build with Tests
mvn clean install
Run the Application Locally (for testing)
java -jar target/SHAFT_MCP-10.2.20260422.jar
Project Structure
SHAFT_MCP/
├── src/
│ ├── main/
│ │ ├── java/io/github/shafthq/SHAFT_MCP/
│ │ │ ├── ShaftMcpApplication.java # Main Spring Boot application
│ │ │ ├── EngineService.java # Driver lifecycle management
│ │ │ ├── BrowserService.java # Browser control tools
│ │ │ ├── ElementService.java # Element interaction tools
│ │ │ ├── BrowserType.java # Browser type enum
│ │ │ └── locatorStrategy.java # Element locator strategies
│ │ └── resources/
│ │ ├── application.properties # STDIO transport (Claude Desktop)
│ │ └── application-http.properties # HTTP/SSE transport (Smithery cloud)
│ └── test/
│ └── java/io/github/shafthq/SHAFT_MCP/
│ ├── ShaftMcpApplicationTests.java
│ └── EngineServiceTest.java
├── pom.xml # Maven configuration
├── Dockerfile # Docker image (downloads JAR from Maven Central)
├── Dockerfile.smithery # Smithery deployment (downloads JAR from Maven Central)
├── Dockerfile.smithery.build # Smithery deployment (multi-stage build from source)
├── smithery.yaml # Smithery.ai configuration
├── server.json # MCP Registry manifest (OCI package listing)
├── SMITHERY_DEPLOYMENT.md # Smithery deployment guide
└── readme.md # User documentation
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.
- 5d ago First seen · 318 lines · 3,288 tokens per session scan A 7cb317a9bce7
SHAFT_MCP copilot-instructions.md is an instructions file published in the GitHub repository ShaftHQ/SHAFT_MCP (8 stars, last pushed 2mo ago), licensed MIT. It adds 3,288 tokens to every session, about $0.0164 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
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
cc-websearch CLAUDE.md
Claude Code instructions for Djarvur/cc-websearch, covering project, constraints, technology stack, what not to add and conventions.
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
sniff AGENTS.md
AGENTS.md instructions for Aboudjem/sniff, covering agents.md: sniff, what this repo is, how an agent should use sniff, handling the playwright setup gate and finding output schema.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).