Claude Code Prompts — Independently Authored Prompt Collection

Independently written prompt templates for building AI coding agents, informed by studying how Claude Code works in practice. System prompts, tool prompts, agent prompts, memory management, and multi-agent coordination.

Claude Code's source was briefly available as a public npm package. We studied the prompting patterns it uses — how it structures safety rules, routes tools, delegates to subagents, manages memory — and wrote our own prompt collection from scratch implementing the same patterns.

Every prompt in this repo is independently authored. We did not copy Anthropic's text. We observed what patterns make a coding agent reliable and wrote our own versions.

Not affiliated with Anthropic. See DISCLAIMER.md.

What's Inside

Quick Start

1. Browse the pattern files to understand how production coding agents structure their prompts.
2. Copy any complete prompt into your own agent configuration.
3. Replace {{PLACEHOLDER}} values with your stack, tool names, and risk policy.
4. For Cursor IDE users, drop skills/ into ~/.cursor/skills-cursor/ for instant integration.

Prompt Engineering Patterns

Patterns observed in how Claude Code structures its prompts — with analysis and independently written templates.

• System Prompt Architecture — layered identity, safety, and behavior
• Core Behavioral Rules — anti-over-engineering, minimal changes
• Safety and Risk Assessment — reversibility tiers, destructive action gates
• Tool-Specific Instructions — per-tool routing and constraints
• Agent Delegation — when and how to spawn subagents
• Verification and Testing — adversarial verification, anti-rationalization
• Memory and Context — summarization, session notes, memory extraction
• Multi-Agent Coordination — coordinator pattern, worker synthesis
• Auxiliary Prompts — utility prompts for titles, recaps, suggestions

Claude Code System Prompt

The complete system prompt covering identity, permissions, task execution, code style, safety, tool routing, tone, and output efficiency.

• System Prompt — the main agent identity and behavioral rules
• Coordinator Prompt — multi-agent orchestration mode

Claude Code Tool Prompts

Prompt templates for each tool a coding agent uses to interact with the filesystem, shell, web, and user.

• Shell Execution — bash command execution with sandbox, git safety, commit/PR workflows
• File Read — reading files, images, PDFs, notebooks
• File Edit — exact string replacement with uniqueness constraints
• File Write — creating new files with read-first safety
• Search Grep — ripgrep-powered content search
• Search Glob — fast file pattern matching
• Web Search — web search with mandatory source citations
• Web Fetch — URL fetching with AI-powered extraction
• Agent Launcher — spawning autonomous subagents
• Ask User — structured multiple-choice questions
• Plan Mode — entering planning mode before implementation

Claude Code Agent Prompts

Prompt templates for specialized subagents — each designed for a different task type.

• General Purpose Agent — research, search, multi-step tasks
• Code Explorer Agent — read-only codebase navigation
• Solution Architect Agent — design and planning
• Verification Specialist Agent — adversarial testing with PASS/FAIL/PARTIAL verdicts
• Documentation Guide Agent — documentation tasks

Claude Code Memory Prompts

How to manage context across long sessions — summarization, session notes, and persistent memory.

• Conversation Summary — 9-section context compression with no-tools constraint
• Session Notes — structured session state tracking
• Memory Extraction — persistent memory from recent messages
• Memory Consolidation — periodic memory cleanup and merging

Claude Code Utility Prompts

Small helper prompts for session management and user experience.

• Session Title — 3-7 word session title generation
• Tool Summary — 30-character tool action summaries
• Away Recap — "while you were away" session recaps
• Next Action Suggestion — suggested follow-up actions

Cursor Skills

Drop-in skills for Cursor IDE that implement these patterns directly.

• Skills Overview
• Coding Agent Standards — behavioral defaults for coding agents
• Verification Agent — adversarial verification workflow (strategies)
• Prompt Architect — prompt design methodology (reference)

Methodology

We studied the prompting patterns used by Claude Code when its source was publicly available as an npm package. We identified the behavioral rules, safety patterns, tool-routing strategies, and multi-agent coordination approaches it employs. We then independently authored every prompt in this repository from scratch, implementing the same patterns in our own words.

No text was copied from Anthropic's codebase. All content is original.

Give Your Agent Codebase Context

The prompts in this repo tell an agent how to behave. But a coding agent also needs to understand the codebase it's working in. RepoWise is an open-source codebase documentation engine that generates structured wikis from any repo, keeps them current as code changes, and exposes everything through an MCP server. Instead of your agent reading 40 raw source files, it calls get_context() and gets architecture docs, dependency graphs, ownership data, and decision records in one shot.

If you're building agents using the patterns from this repo, RepoWise gives them the codebase intelligence to actually be effective: github.com/repowise-dev/repowise

Legal

• DISCLAIMER.md — independent authorship, nominative fair use, non-affiliation, DMCA policy.
• LICENSE — MIT for all original content.
• CHANGELOG.md — version history.

"Claude Code" is a trademark of Anthropic, used here under nominative fair use to describe the subject matter. This project is independent — we are not Anthropic, and these are not Anthropic's prompts. They are our own prompts, informed by studying how Claude Code works.

Contributing

• All additions must be original writing. No verbatim vendor prompt text.
• Prefer concise, implementation-ready language over theory.
• Every new pattern file must include at least one concrete template.
• Follow section conventions: Approach / Output / Constraints for agents, Include / Format / Constraints for memory, Rules / Format for utilities.

Star History

If this helped you build better AI agents, star the repo so others can find it.