docs: rename copilot-instructions.md to agents.md

.github/workflows/copilot-setup-steps.yml

@@ -0,0 +1,51 @@
+# https://docs.github.com/en/copilot/customizing-copilot/customizing-the-development-environment-for-copilot-coding-agent
+name: "Copilot Setup Steps"
+
+on:
+  workflow_dispatch:
+  push:
+    paths:
+      - .github/workflows/copilot-setup-steps.yml
+  pull_request:
+    paths:
+      - .github/workflows/copilot-setup-steps.yml
+
+jobs:
+  copilot-setup-steps:
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: read
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Go
+        uses: actions/setup-go@v5
+        with:
+          go-version-file: go.mod
+
+      - name: Download Go dependencies
+        run: go mod download
+
+      - name: Build server
+        run: go build -v ./cmd/github-mcp-server
+
+      - name: Install goimports
+        run: go install golang.org/x/tools/cmd/goimports@latest
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '22'
+
+      - name: Install MCP Inspector
+        run: npm install -g @modelcontextprotocol/inspector@0.7.0
+
+      - name: Verify tools
+        run: |
+          echo "Go version: $(go version)"
+          echo "goimports: $(which goimports)"
+          echo "MCP Inspector: $(which mcp-inspector || echo 'installed via npx')"
+          echo "Server binary: $(ls -la github-mcp-server)"

.github/copilot-instructions.md → AGENTS.md

@@ -1,4 +1,16 @@
-# GitHub MCP Server - Copilot Instructions
+# GitHub MCP Server - Agent Instructions
+
+> This file follows the [agents.md](https://agents.md) convention for AI agent instructions.
+
+## AI Disclosure Requirement
+
+> **If you are using AI assistance to contribute to this repository, you must disclose it in the pull request or issue body.**
+
+Include a brief statement like:
+- "This PR was written with assistance from [agent name]."
+- "I used [tool] to help generate this code."
+
+This helps maintainers understand the context and apply appropriate review scrutiny.
 
 ## Project Overview
 
@@ -59,6 +71,29 @@ go test ./pkg/github -v
 go test ./pkg/github -run TestGetMe
 ```
 
+### Testing with MCP Inspector
+
+Use the [MCP Inspector](https://github.com/modelcontextprotocol/inspector) CLI to test the server:
+
+```bash
+# Build the server first
+go build -v ./cmd/github-mcp-server
+
+# List available tools
+npx @modelcontextprotocol/inspector@0.7.0 --cli \
+  --config '{"mcpServers":{"github":{"command":"./github-mcp-server","args":["stdio"],"env":{"GITHUB_PERSONAL_ACCESS_TOKEN":"your-token"}}}}' \
+  --server github \
+  --method tools/list
+
+# Call a specific tool (e.g., get authenticated user)
+npx @modelcontextprotocol/inspector@0.7.0 --cli \
+  --config '{"mcpServers":{"github":{"command":"./github-mcp-server","args":["stdio"],"env":{"GITHUB_PERSONAL_ACCESS_TOKEN":"your-token"}}}}' \
+  --server github \
+  --method tools/call --tool-name get_me
+```
+
+Note: Replace `your-token` with a valid GitHub Personal Access Token.
+
 ## Project Structure
 
 ### Directory Layout

CONTRIBUTING.md

@@ -56,3 +56,18 @@ Here are a few things you can do that will increase the likelihood of your pull
 - [How to Contribute to Open Source](https://opensource.guide/how-to-contribute/)
 - [Using Pull Requests](https://help.github.com/articles/about-pull-requests/)
 - [GitHub Help](https://help.github.com)
+
+## AI Contributions
+
+We welcome contributions that use AI assistance. However, **if you are using any kind of AI assistance** (e.g., GitHub Copilot, Claude, ChatGPT, or other AI agents), **you must disclose this in your pull request or issue**.
+
+Include a brief statement describing:
+- Which AI tool(s) you used
+- The extent of AI assistance (e.g., "code generation", "documentation help", "debugging suggestions")
+
+Example disclosures:
+> This PR was written with assistance from GitHub Copilot.
+
+> I used Claude to help draft the initial implementation, which I then reviewed and modified.
+
+This transparency helps maintainers understand context and apply appropriate review. Trivial fixes (typos, formatting) don't require disclosure.