#446446th of 455 in Skills, plugins and prompts
claude-code-prompts
Markdown prompt templates for coding agents, modeled on Claude Code patterns
- Stars
- 1.2k
- License
- MIT
- Last commit
- May 2026
937 on 22 Apr 20261,227 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A collection of markdown prompts for coding agents: one system prompt, 11 tool prompts, 5 subagent prompts, 4 memory prompts, a multi-agent coordinator prompt and 4 utility prompts. It also has 9 pattern write-ups and 3 Cursor skills. The authors say all text is written independently rather than copied from Claude Code, and templates use {{PLACEHOLDER}} values for your stack and risk policy.
Who it is for: Developers writing system and tool prompts for their own coding agents
Strengths
- Covers system, tool, subagent, memory and coordinator prompts in one repo
- Each pattern file includes a concrete reusable template
- Copy-and-edit use with {{PLACEHOLDER}} values, no runtime needed
- Includes 3 drop-in Cursor skills for standards, verification and prompt design
Weaknesses
- Prompts only; no code, tests or evals to check they work
- Modeled on observed Claude Code behavior, not an official or affiliated source
- README promotes the authors' RepoWise product throughout
- No tagged releases; version history only in CHANGELOG.md
What it needs
- no GPU
Also in Skills, plugins and prompts
See all 455| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |