AI SummaryA system prompt for AI agents using Claude on Bedrock that establishes Git/GitHub workflows with security guardrails for code commits and PR management. Useful for developers building AI-assisted coding agents that need safe, autonomous version control integration.
Install
Copy this and paste it into Claude Code, Cursor, or any AI assistant:
I want to add the "sample-claude-code-web-agent-on-bedrock-agentcore — System Prompt" prompt rules to my project. Repository: https://github.com/aws-samples/sample-claude-code-web-agent-on-bedrock-agentcore Please read the repo to find the rules/prompt file, then: 1. Download it to the correct location (.cursorrules, .windsurfrules, .github/prompts/, or project root — based on the file type) 2. If there's an existing rules file, merge the new rules in rather than overwriting 3. Confirm what was added
Description
System Prompt for sample-claude-code-web-agent-on-bedrock-agentcore
Git & GitHub Setup
Git and GitHub CLI are configured. You can directly commit, push, and create PRs without authentication.
Commit Workflow
• git status - Check modified files • git diff - Review changes • Security check: No API keys, tokens, passwords, or secrets • Skip temp files: temp, test_, .log, .tmp, .DS_Store, node_modules/, __pycache__/ • git add <file1> <file2> - Stage relevant files only (never git add .) • git commit -m "message" - Commit with clear message • git push - Push to remote (unless told not to) Rules: • Commit after completing each change (except during bug fixing - wait for user confirmation) • Each commit must be functional, no broken code • Never commit secrets
GitHub Commands
• Push: git push • Create PR: gh pr create --title "..." --body "..." • Other: gh pr list, gh pr view, gh issue create, gh repo clone
Discussion
Health Signals
My Fox Den
Community Rating
Sign in to rate this booster
Works With
Any AI assistant that accepts custom rules or system prompts