{"id":49071240,"url":"https://github.com/repowise-dev/claude-code-prompts","last_synced_at":"2026-04-20T07:33:45.470Z","repository":{"id":348493298,"uuid":"1198155461","full_name":"repowise-dev/claude-code-prompts","owner":"repowise-dev","description":"Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination. Informed by studying Claude Code.","archived":false,"fork":false,"pushed_at":"2026-04-09T18:04:22.000Z","size":388,"stargazers_count":898,"open_issues_count":0,"forks_count":345,"subscribers_count":18,"default_branch":"master","last_synced_at":"2026-04-09T20:08:14.490Z","etag":null,"topics":["ai-coding-agent","ai-tools","anthropic-claude","claude-code","claude-code-prompts","claude-code-system-prompt","claude-prompts","coding-assistant","cursor-skills","llm-prompts","multi-agent","prompt-engineering","prompt-templates","system-prompt"],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/repowise-dev.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-04-01T06:59:09.000Z","updated_at":"2026-04-09T20:02:24.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/repowise-dev/claude-code-prompts","commit_stats":null,"previous_names":["repowise-dev/claude-code-prompts"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/repowise-dev/claude-code-prompts","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/repowise-dev%2Fclaude-code-prompts","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/repowise-dev%2Fclaude-code-prompts/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/repowise-dev%2Fclaude-code-prompts/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/repowise-dev%2Fclaude-code-prompts/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/repowise-dev","download_url":"https://codeload.github.com/repowise-dev/claude-code-prompts/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/repowise-dev%2Fclaude-code-prompts/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32037891,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-20T00:18:06.643Z","status":"online","status_checked_at":"2026-04-20T02:00:06.527Z","response_time":94,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-coding-agent","ai-tools","anthropic-claude","claude-code","claude-code-prompts","claude-code-system-prompt","claude-prompts","coding-assistant","cursor-skills","llm-prompts","multi-agent","prompt-engineering","prompt-templates","system-prompt"],"created_at":"2026-04-20T07:33:41.806Z","updated_at":"2026-04-20T07:33:45.463Z","avatar_url":"https://github.com/repowise-dev.png","language":null,"funding_links":[],"categories":["Others"],"sub_categories":[],"readme":"# Claude Code Prompts — Independently Authored Prompt Collection\n\n\u003e Independently written prompt templates for building AI coding agents, inspired by patterns observed in Claude Code. System prompts, tool prompts, agent prompts, memory management, and multi-agent coordination.\n\n## Check out [RepoWise](https://github.com/repowise-dev/repowise)\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/repowise-dev/repowise\"\u003e\n    \u003cimg src=\"./assets/repowise-logo.png\" alt=\"RepoWise\" width=\"140\" /\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n**Prompts tell your agent how to behave. [RepoWise](https://github.com/repowise-dev/repowise) tells it what the codebase actually does.**\n\nOpen-source codebase intelligence engine. Auto-generated architecture wikis, dependency graphs, ownership maps, dead code detection, and 9 MCP tools your AI editor can query in real time.\n\n**[GitHub](https://github.com/repowise-dev/repowise)** \u0026nbsp; | \u0026nbsp; [repowise.dev](https://repowise.dev)\n\nScroll down for Claude Code's prompt patterns. 👇\n\n---\n\n\u003c!-- GitHub repo description: Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination. Informed by observing how Claude Code works in practice. --\u003e\n\n\u003c!-- Suggested GitHub topics: claude-code, claude-code-prompts, claude-prompts, system-prompt, claude-code-system-prompt, prompt-engineering, anthropic-claude, ai-coding-agent, claude-agent, llm-prompts, ai-prompts, cursor-skills, multi-agent, coding-assistant, ai-tools, prompt-templates --\u003e\n\n## Claude Code System Prompts\n\nWe studied how Claude Code behaves in practice -- how it structures safety rules, routes tools, delegates to subagents, manages memory -- and wrote our own prompt collection from scratch implementing the same patterns.\n\n**Every prompt in this repo is independently authored.** We observed what patterns make a coding agent reliable and wrote our own versions. From the team behind [RepoWise](https://github.com/repowise-dev/repowise).\n\nNot affiliated with Anthropic. See [DISCLAIMER.md](./DISCLAIMER.md).\n\n\u003e **Note**\n\u003e ⭐ Star this repository to if you find the collection useful.\n\n## What's Inside\n\n| Category | Files | What You Get |\n|----------|-------|--------------|\n| [System prompt](#claude-code-system-prompt-1) | 1 | Agent identity, safety rules, code style, tool routing, output format |\n| [Tool prompts](#claude-code-tool-prompts) | 11 | Shell, file read/edit/write, grep, glob, web search/fetch, agent launcher, ask user, plan mode |\n| [Agent prompts](#claude-code-agent-prompts) | 5 | General purpose, code explorer, solution architect, verification specialist, documentation guide |\n| [Memory prompts](#claude-code-memory-prompts) | 4 | Conversation summarization, session notes, memory extraction, memory consolidation |\n| [Coordinator prompt](#multi-agent-coordinator) | 1 | Multi-worker orchestration with synthesis, delegation, and verification workflow |\n| [Utility prompts](#claude-code-utility-prompts) | 4 | Session titles, tool summaries, away recaps, next-action suggestions |\n| [Pattern analyses](#prompt-engineering-patterns) | 9 | Commentary on each pattern with reusable templates |\n| [Cursor skills](#cursor-skills) | 3 | Drop-in skills for coding standards, verification, and prompt design |\n\n## Quick Start\n\n1. Browse the [pattern files](#prompt-engineering-patterns) to understand how production coding agents structure their prompts.\n2. Copy any [complete prompt](#claude-code-system-prompt-1) into your own agent configuration.\n3. Replace `{{PLACEHOLDER}}` values with your stack, tool names, and risk policy.\n4. For Cursor IDE users, drop `skills/` into `~/.cursor/skills-cursor/` for instant integration.\n5. Add codebase context with [RepoWise](https://github.com/repowise-dev/repowise) so your agent actually understands the project it's working in.\n\n## Prompt Engineering Patterns\n\nPatterns observed in how Claude Code structures its prompts — with analysis and independently written templates.\n\n- [System Prompt Architecture](./patterns/01-system-prompt-architecture.md) — layered identity, safety, and behavior\n- [Core Behavioral Rules](./patterns/02-core-behavioral-rules.md) — anti-over-engineering, minimal changes\n- [Safety and Risk Assessment](./patterns/03-safety-and-risk-assessment.md) — reversibility tiers, destructive action gates\n- [Tool-Specific Instructions](./patterns/04-tool-specific-instructions.md) — per-tool routing and constraints\n- [Agent Delegation](./patterns/05-agent-delegation.md) — when and how to spawn subagents\n- [Verification and Testing](./patterns/06-verification-and-testing.md) — adversarial verification, anti-rationalization\n- [Memory and Context](./patterns/07-memory-and-context.md) — summarization, session notes, memory extraction\n- [Multi-Agent Coordination](./patterns/08-multi-agent-coordination.md) — coordinator pattern, worker synthesis\n- [Auxiliary Prompts](./patterns/09-auxiliary-prompts.md) — utility prompts for titles, recaps, suggestions\n\n## Claude Code System Prompt\n\nThe complete system prompt covering identity, permissions, task execution, code style, safety, tool routing, tone, and output efficiency.\n\n- [System Prompt](./complete-prompts/system-prompt.md) — the main agent identity and behavioral rules\n- [Coordinator Prompt](./complete-prompts/coordinator-prompt.md) — multi-agent orchestration mode\n\n## Claude Code Tool Prompts\n\nPrompt templates for each tool a coding agent uses to interact with the filesystem, shell, web, and user.\n\n- [Shell Execution](./complete-prompts/tool-prompts/shell-execution.md) — bash command execution with sandbox, git safety, commit/PR workflows\n- [File Read](./complete-prompts/tool-prompts/file-read.md) — reading files, images, PDFs, notebooks\n- [File Edit](./complete-prompts/tool-prompts/file-edit.md) — exact string replacement with uniqueness constraints\n- [File Write](./complete-prompts/tool-prompts/file-write.md) — creating new files with read-first safety\n- [Search Grep](./complete-prompts/tool-prompts/search-grep.md) — ripgrep-powered content search\n- [Search Glob](./complete-prompts/tool-prompts/search-glob.md) — fast file pattern matching\n- [Web Search](./complete-prompts/tool-prompts/web-search.md) — web search with mandatory source citations\n- [Web Fetch](./complete-prompts/tool-prompts/web-fetch.md) — URL fetching with AI-powered extraction\n- [Agent Launcher](./complete-prompts/tool-prompts/task-management.md) — spawning autonomous subagents\n- [Ask User](./complete-prompts/tool-prompts/ask-user.md) — structured multiple-choice questions\n- [Plan Mode](./complete-prompts/tool-prompts/plan-mode.md) — entering planning mode before implementation\n\n## Claude Code Agent Prompts\n\nPrompt templates for specialized subagents — each designed for a different task type.\n\n- [General Purpose Agent](./complete-prompts/agent-prompts/general-purpose.md) — research, search, multi-step tasks\n- [Code Explorer Agent](./complete-prompts/agent-prompts/code-explorer.md) — read-only codebase navigation\n- [Solution Architect Agent](./complete-prompts/agent-prompts/solution-architect.md) — design and planning\n- [Verification Specialist Agent](./complete-prompts/agent-prompts/verification-specialist.md) — adversarial testing with PASS/FAIL/PARTIAL verdicts\n- [Documentation Guide Agent](./complete-prompts/agent-prompts/documentation-guide.md) — documentation tasks\n\n## Claude Code Memory Prompts\n\nHow to manage context across long sessions — summarization, session notes, and persistent memory.\n\n- [Conversation Summary](./complete-prompts/memory-prompts/conversation-summary.md) — 9-section context compression with no-tools constraint\n- [Session Notes](./complete-prompts/memory-prompts/session-notes.md) — structured session state tracking\n- [Memory Extraction](./complete-prompts/memory-prompts/memory-extraction.md) — persistent memory from recent messages\n- [Memory Consolidation](./complete-prompts/memory-prompts/memory-consolidation.md) — periodic memory cleanup and merging\n\n## Claude Code Utility Prompts\n\nSmall helper prompts for session management and user experience.\n\n- [Session Title](./complete-prompts/utility-prompts/session-title.md) — 3-7 word session title generation\n- [Tool Summary](./complete-prompts/utility-prompts/tool-summary.md) — 30-character tool action summaries\n- [Away Recap](./complete-prompts/utility-prompts/away-recap.md) — \"while you were away\" session recaps\n- [Next Action Suggestion](./complete-prompts/utility-prompts/next-action-suggestion.md) — suggested follow-up actions\n\n## Cursor Skills\n\nDrop-in skills for Cursor IDE that implement these patterns directly.\n\n- [Skills Overview](./skills/README.md)\n- [Coding Agent Standards](./skills/coding-agent-standards/SKILL.md) — behavioral defaults for coding agents\n- [Verification Agent](./skills/verification-agent/SKILL.md) — adversarial verification workflow ([strategies](./skills/verification-agent/strategies.md))\n- [Prompt Architect](./skills/prompt-architect/SKILL.md) — prompt design methodology ([reference](./skills/prompt-architect/reference.md))\n\n## Methodology\n\nWe studied how Claude Code behaves in practice and identified the behavioral rules, safety patterns, tool-routing strategies, and multi-agent coordination approaches that make it effective. We then independently authored every prompt in this repository from scratch, implementing the same patterns in our own words.\n\nAll content is original.\n\n## Pair With RepoWise for Full-Stack Agent Intelligence\n\nThe prompts in this repo handle agent behavior: safety, tool routing, delegation, verification. But behavior without context is like a senior engineer who's never seen the codebase. [RepoWise](https://github.com/repowise-dev/repowise) fills that gap.\n\n| What you get | How it helps your agent |\n|---|---|\n| Architecture wiki | Agent understands module boundaries before making changes |\n| Dependency graphs | Agent traces impact of changes across packages |\n| Ownership tracking | Agent knows which team/person owns each module |\n| Dead code detection | Agent avoids modifying unused code paths |\n| 9 MCP tools | Agent queries project knowledge directly from Cursor, Claude Code, or any MCP-compatible editor |\n\nWorks with any language, any repo size.\n\n**[GitHub](https://github.com/repowise-dev/repowise)** | [repowise.dev](https://repowise.dev)\n\n## Legal\n\n- [DISCLAIMER.md](./DISCLAIMER.md) — independent authorship, nominative fair use, non-affiliation, DMCA policy.\n- [LICENSE](./LICENSE) — MIT for all original content.\n- [CHANGELOG.md](./CHANGELOG.md) — version history.\n\n\"Claude Code\" is a trademark of Anthropic, used here under nominative fair use to describe the subject matter. This project is independent and not affiliated with Anthropic.\n\n## Contributing\n\n- All additions must be original writing. No verbatim vendor prompt text.\n- Prefer concise, implementation-ready language over theory.\n- Every new pattern file must include at least one concrete template.\n- Follow section conventions: `Approach / Output / Constraints` for agents, `Include / Format / Constraints` for memory, `Rules / Format` for utilities.\n\n## Star History\n\nIf this helped you build better AI agents, star the repo so others can find it.\n\n---\n\n**Built by [RepoWise](https://github.com/repowise-dev/repowise)** — open-source codebase intelligence for AI agents ([repowise.dev](https://repowise.dev)).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frepowise-dev%2Fclaude-code-prompts","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frepowise-dev%2Fclaude-code-prompts","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frepowise-dev%2Fclaude-code-prompts/lists"}