Agent Prompts Warmup
Audit and sync agent instruction files across all coding agent formats. FRE (first-run) checks scaffolding completeness; ongoing use keeps files in sync after edits.
- Type
- Skill
- Repository
- iamtouchskyer/memex
- GitHub stars
- 142
- License
- MIT
- Repo last updated
- Sep 8, 2026
- Source file
- skills/agent-prompts-warmup/SKILL.md
What Agent Prompts Warmup is
Agent Prompts Warmup is a skill published in the iamtouchskyer/memex repository on GitHub, which has about 142 stars. The repository describes itself as: “Zettelkasten-based persistent memory for AI coding agents. Works with Claude Code, Cursor, VS Code Copilot, Codex, Windsurf & any MCP client. No vector DB — just markdown + git sync.”
A skill is a folder with a SKILL.md file: frontmatter with a name and a description, followed by instructions Claude follows. Claude loads a skill automatically when a task matches its description, and you can also run it directly with a slash and its name.
Skills work in Claude Code and in Claude Cowork, which makes Agent Prompts Warmup a portable way to give Claude the same method everywhere.
How to install Agent Prompts Warmup
Claude Code
- Download the agent-prompts-warmup folder from the repository.
- Save it as ~/.claude/skills/<skill-name>/SKILL.md for all projects, or .claude/skills/<skill-name>/SKILL.md for one project.
- Claude loads it automatically when a task matches; you can also run it with / and its name.
Claude Cowork
- Zip the skill folder so SKILL.md sits at the top level of the folder.
- Open Customize → Skills, click +, then upload the ZIP.
- Start a task that matches the description, or call it by name with /.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from skills/agent-prompts-warmup/SKILL.md, shared under the repository's MIT license. Read the full file on GitHub.
Agent instruction files ensure every coding agent (Claude Code, Codex, Copilot, Cursor, Gemini, Windsurf/Anti-Gravity) reads the same project rules when working on this codebase.
Architecture
Single source of truth: AGENTS.md
All other files are copies, synced automatically:
Sync mechanisms (4 layers):
- scripts/postbuild.mjs — npm run build copies AGENTS.md → all targets
- scripts/pre-commit — git hook blocks commit if any file has drifted
- tests/integration/agent-docs-consistency.test.ts — npm test fails on drift
- CI — GitHub Actions runs npm test on push/PR to main
When To Use This Skill
1. FRE Audit (first run in a new clone/worktree)
Run a full scaffolding check:
/agent-prompts-warmup auditChecklist to verify:
- AGENTS.md exists and is non-empty
- All target files exist: CLAUDE.md, GEMINI.md, .cursorrules, .windsurfrules
- All targets are byte-identical to AGENTS.md (diff -q)
- scripts/postbuild.mjs has cpSync lines for all targets
- tests/integration/agent-docs-consistency.test.ts tests all targets
- scripts/pre-commit exists and checks all targets
- .git/hooks/pre-commit is installed and executable (run npm run prepare if not)
- package.json files field includes AGENTS.md, CLAUDE.md, GEMINI.md, docs
- package.json has "prepare" script that installs the hook
If anything fails: fix it immediately. The fix is usually npm run build (syncs files) or npm run prepare (installs hook).
2. After Editing Instructions
When the user edits AGENTS.md (or asks you to):
- Edit only AGENTS.md — never edit the copies directly
- Run sync: node scripts/postbuild.mjs (or npm run build)
- Verify: npm test -- tests/integration/agent-docs-consistency.test.ts
- Confirm all 5 files are identical
3. Adding a New Agent Target
When a new coding agent emerges that reads a different file:
- Identify the file name the agent reads (e.g., .devinrules, CLINE.md)
- Update scripts/postbuild.mjs — add cpSync("AGENTS.md", " ");
- Update tests/integration/agent-docs-consistency.test.ts — add expect(readFileSync(" ", "utf-8")).toBe(agents);
- Update scripts/pre-commit — add the new file to the TARGETS array
- Create the file: cp AGENTS.md
- If it should be npm-published: add to package.json files array
- Run npm test to verify
- Update this skill's mapping table above
Troubleshooting
"ERROR: CLAUDE.md has drifted from AGENTS.md" → Someone edited a copy instead of AGENTS.md. Fix: cp AGENTS.md CLAUDE.md (or whichever file drifted). Then check if the edit in the copy should be applied — if so, edit AGENTS.md first, then npm run build.
Pre-commit hook not running → npm run prepare to reinstall. Or manually: cp scripts/pre-commit .git/hooks/pre-commit && chmod +x .git/hooks/pre-commit
CI failing on agent docs → npm run build && npm test locally. If it passes locally but fails in CI, check that the build step runs before test in the workflow.
Current Mapping Reference
// scripts/postbuild.mjs
cpSync("AGENTS.md", "CLAUDE.md"); // Claude Code
cpSync("AGENTS.md", "GEMINI.md"); // Gemini CLI / Jules / Anti-Gravity
cpSync("AGENTS.md", ".cursorrules"); // Cursor
cpSync("AGENTS.md", ".windsurfrules"); // Windsurf / Anti-Gravity (legacy) Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is Agent Prompts Warmup?
Agent Prompts Warmup is a skill for Claude Code and Claude Cowork from the iamtouchskyer/memex repository on GitHub. Audit and sync agent instruction files across all coding agent formats. FRE (first-run) checks scaffolding completeness; ongoing use keeps files in sync after edits.
How do I install Agent Prompts Warmup in Claude Code?
Download the agent-prompts-warmup folder from the repository. Save it as ~/.claude/skills/<skill-name>/SKILL.md for all projects, or .claude/skills/<skill-name>/SKILL.md for one project. Claude loads it automatically when a task matches; you can also run it with / and its name.
Can I use Agent Prompts Warmup in Claude Cowork?
Zip the skill folder so SKILL.md sits at the top level of the folder. Open Customize → Skills, click +, then upload the ZIP. Start a task that matches the description, or call it by name with /.
Is Agent Prompts Warmup safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- Memex Zettelkasten-based agent memory system with bidirectional links Plugin · iamtouchskyer/memex
- Claude Code Terminal Title Gives each Claud-Code terminal window a dynamic title that describes the work being done so you don't lose track of what window is doing… Skill · bluzername/claude-code-terminal-title
- Accessing Github Repos GitHub repository access in containerized environments using REST API and credential detection. Use when git clone fails, or when accessing private repos/writing files via API. Skill · oaustegard/claude-skills
- Cloudflare Self-contained deploy automation — invoke directly, do not decompose. Deploys a Vibes app to Cloudflare Workers via the Deploy API. Use when deploying, publishing, going live, pushing to production, or hosting on the edge. Skill · popmechanic/VibesOS
- Create Mode Author a new Pneuma mode end-to-end — manifest + viewer + skill + seed + showcase. Use this skill whenever the user says they want to… Skill · pandazki/pneuma-skills
- 00 Andruia Consultant Arquitecto de Soluciones Principal y Consultor Tecnológico de Andru.ia. Diagnostica y traza la hoja de ruta óptima para proyectos de IA en… Skill · sickn33/antigravity-awesome-skills
- Abort Safe Handler Orchestrator-level Stage 4 entry gate for /gaai:bootstrap. Presents a pre-loop 'Skip Q&A entirely' option, delegates to qa-loop-ui when the user proceeds, and returns a unified abort_safe_result with telemetry on every path. Guarantees no partial state on skip or abort. Skill · digipulse-engineering/GAAI-framework
- Agents Best Practices Use this skill when designing, generating an MVP blueprint for, auditing, refactoring, or explaining an agentic harness for any domain.… Skill · DenisSergeevitch/agents-best-practices