Reusable prompt templates, multi-step workflow chains, and quality gates for any MCP client.
io.github.minipuft/claude-prompts-mcp — Model Context Protocol (MCP) Server
The server provides reusable prompt templates for MCP clients, including multi-step workflow chains and quality gates. It is positioned as a portable workflow layer alongside an AI coding harness, where the client executes with its own tools, agents, and context.
🛠️ Key Features
Reusable prompt templates
Composable, multi-step workflow chains
Validation/quality gates for prompts or workflows
🚀 Use Cases
Building AI workflows in MCP clients
Reusing prompt resources across LLM tooling and agentic flows
⚡ Developer Benefits
Prompt management via reusable templates
Prompt composition using chain-based workflow design
The portable workflow layer beside your AI coding harness.
Your client executes with its own tools, agents, and context.
Claude Prompts adds reusable prompt resources, composable chains, validation gates, and client-native skill export.
What your AI client gives you — and what this server adds
Your client already does
This server adds
Run a prompt
Compose prompts with validation, reasoning guidance, and formatting in one expression
Single-shot skills
Multi-step workflows that thread context between steps
Execute subagents
Hand off mid-chain steps to agents with full workflow context
Client-native skill format
Author once as YAML, export to any client with skills:export
Manual prompt writing
Versioned templates with hot-reload, rollback, and history
Trust the output
Validate output between steps: self-evaluation and shell commands
Is this for me?
Use this if you write the same prompts repeatedly, run multi-step workflows, or want to share reusable prompts with a team.
Skip if your client's built-in /commands already handle what you need, or you're looking for a no-code prompt library.
Works with Claude Code, Claude Desktop, Cursor, VS Code, OpenCode, Gemini CLI, Codex, and Windsurf. Hook coverage differs by client; the client list shows it.
Quick Start
Claude Code (Recommended)
bash
/plugin marketplace add minipuft/minipuft-plugins # first time only
/plugin install claude-prompts@minipuft
>>tech_evaluation_chain library:'zod' context:'API validation'
Codex (Experimental)
Turn on hooks in ~/.codex/config.toml, then install the plugin:
Restart Codex, run /hooks to review and trust the plugin hooks, then try the same >>tech_evaluation_chain command. Needs Codex CLI 0.117 or later; not available on Windows (requirements).
Every Client
All 8 clients: setup and hook coverage 2 full · 1 experimental · 1 partial · 4 MCP tools only
Hooks are what make >>, -->, and :: work in conversation; "MCP tools only" means the three MCP tools without them. See With Hooks. Config locations and --client presets: Client Capabilities Reference.
Hooks: MCP tools onlyClaude DesktopDesktop bundle or npx config
Option A: GitHub Release (recommended): download claude-prompts-{version}.mcpb from Releases and drag it into Claude Desktop Settings → MCP Servers. The .mcpb bundle is self-contained (~5MB); no npm required.
Option B: NPX (auto-updates): add this to your config file (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json, Windows: %APPDATA%\Claude\claude_desktop_config.json):
Restart Claude Desktop and test: >>research_chain topic:'remote team policies'
Hooks: MCP tools onlyCursor, VS Code, WindsurfMCP config
Cursor and Windsurf (now Devin Desktop) use the same block. Add it to ~/.cursor/mcp.json for Cursor, or to ~/.config/devin/mcp_config.json for Windsurf (Windows: %APPDATA%\devin\mcp_config.json):
Four primitives you author, version, and compose. The bundled set ships 52 prompts across 9 categories — a starting library, not the ceiling: your AI writes new prompts and chains through resource_manager as it works, so the set grows around what you actually do. All hot-reloadable, all versioned with rollback.
Primitive
Symbol
What it is
Example
Prompt template
>>
Versioned YAML with named arguments; hot-reload on save
>>review target:'src/auth/'
Gate
::
Validation criterion the AI checks its own output against; blocking or advisory; can shell-verify
:: 'cite sources' · :: verify:"npm test"
Framework
^
Reasoning framework that shapes how the AI works through the problem; plug in your own or use built-ins like ^ReACT, ^5W1H, or the project's own ^CAGEERF scaffold (Frameworks Guide)
^ReACT · ^your_framework
Style
#
Output formatting and tone
#analytical · #procedural
Prompts, gates, and frameworks are managed through the resource_manager tool. Your AI creates, edits, versions, and rolls them back through MCP, no file editing required. Styles are managed with the bundled cpm CLI. Failed gate checks can retry automatically or pause for your decision (Gates Guide). Build your first primitive: Prompt Authoring Tutorial.
Your own prompts
Your own prompts, gates and frameworks live in a workspace you choose. --init=~/my-prompts scaffolds a starter workspace: three example prompts plus config.jsonc. Edit them (YAML schema), or have your AI author new prompts, gates, and frameworks via resource_manager. Point MCP_RESOURCES_PATH at an existing workspace if you already have one in the right shape. Resources that belong to one repository go in .claude-prompts/ at its root (cpm init --project scaffolds it) and load above your workspace over STDIO. See Custom Resources Guide.
The Three Tools
Everything above reaches your client through three MCP tools:
Tool
Purpose
prompt_engine
Execute prompts with frameworks and validation
resource_manager
Create, update, version, and roll back resources
system_control
Status, analytics, framework switching
Most users invoke these via >> syntax in conversation; hooks construct the actual calls. For programmatic MCP clients calling tools directly, see MCP Tools Reference.
>>review target:'src/auth/' runs the review prompt against your auth folder.
^ReACT overlays the ReACT reasoning framework on this step.
:: 'cite sources' adds a gate the AI must satisfy (cite sources, or retry).
--> security_scan :: verify:"npm test" chains to step 2, which must pass npm test before producing output.
==> implementation hands the final step off to a client-native agent (a subagent in Claude Code).
review ships with the server; security_scan and implementation stand in for prompts you write.
Validation runs between steps, not only at the end. For the full operator grammar and examples, see MCP Tools Reference.
No video player here? Open the GIF.One Claude Code session, with a side panel showing what the hooks and the server do: npm test fails, >>status is routed by the hook, resource_manager creates a prompt, a two-step chain runs it under ^ReACT, the server runs npm test as the gate, and the review step approves the result
Recorded live in Claude Code (Sonnet), sped up, nothing re-ordered or retyped. The side panel shows what each hook and the server's npm test gate did.
Two patterns extend the basic syntax. Chains also support context threading between steps and agent handoffs. See Chains Lifecycle and MCP Tools Reference.
See the output: tech evaluation chain with context7 research Tech evaluation chain researching Zod via context7, producing a scored assessment table with security, performance, DX, integration, and ecosystem ratings
Context7 fetches live library docs mid-chain. The final output is a structured assessment with sources.
Verification Loops
Ground-truth validation via shell commands. The AI keeps iterating until tests pass:
Implements, runs the test, reads failures, fixes, retries. Spawns a fresh context after repeated failures to avoid context rot.
implement-feature stands for your own prompt: :: verify attaches to any of them.
Preset
Tries
Timeout
Use Case
:fast
1
30s
Quick check
:full
5
5 min
CI validation
:extended
10
10 min
Large test suites
For autonomous test-fix cycles with context-rot prevention: Ralph Loops Guide.
Judge Mode
Let the AI pick the right resources for the task:
code
%judge Help me refactor this authentication module
Analyzes available templates, reasoning frameworks, validation rules, and styles, then recommends the best combination. You confirm before it runs. For scoring and overrides see Judge Mode Guide.
Run Anywhere
Author workflows as YAML templates. Export as native skills to your client.
yaml
# skills-sync.yaml — choose what to exportregistrations:claude-code:user:-prompt:development/review-prompt:development/validate_work
bash
npm run skills:export
The review prompt becomes a /review Claude Code skill. validate_work becomes /validate_work. Same source, native experience; no MCP call required at runtime.
Compiles to native skill packages for Claude Code, Cursor, Codex and OpenCode. npm run skills:diff flags when exports drift from source. Configuration, supported clients, and drift detection: Skills Sync Guide.
With Hooks
Without hooks, you're calling the three MCP tools explicitly (the LLM constructs each call). With hooks, the operators work in conversation: >>, -->, ==>, :: feel native rather than mediated, and workflow state survives across LLM turns and context compaction.
What hooks unlock:
Hook
Unlocks
Auto-routing
>>research_chain topic:'X' in chat fires the right MCP tool call without you naming it
Chain continuity across compaction
Multi-step chains preserve state when context compacts mid-execution; the chain doesn't restart from scratch
Cross-step verdict tracking
Gate pass/fail verdicts thread across all chain steps without the LLM re-deriving them
Native agent handoffs
==> routes to your client's subagent system automatically; no manual subagent invocation
Session persistence
Workflow state preserved when context compacts mid-chain
Hooks ship with the plugin install; the client list shows which clients have them. Detail: hooks/README.md.
How It Works
Command with operators → server parses and injects resources (framework, gates, style) → client executes the rendered prompt and self-evaluates against the gates → router decides: next step on pass, retry on fail, return on done.
Full request lifecycle, pipeline stages, and subsystem diagrams: Architecture Overview.
Documentation
Choose a guide based on what you want to do: learn by building, complete a task, look up syntax, or understand the design.
Run it from source, as a Claude Code plugin or for any other MCP client:
bash
git clone https://github.com/minipuft/claude-prompts-mcp.git && cd claude-prompts-mcp
(cd server && npm install && npm run build) # esbuild bundles to server/dist/index.js
claude --plugin-dir . # load it as a Claude Code plugin
For any other MCP client, point its config at server/dist/index.js; transport is --transport=stdio (default) or --transport=streamable-http. Edit hooks or prompts → restart the client. Edit TypeScript → rebuild first.
bash
cd server
npm test# Run test suite
npm run validate:all # Full CI validation
The build produces a self-contained bundle. server/dist/ is gitignored, and CI builds fresh from source.