Plugin Claude Code
Plugin marketplace listing 1 plugin: ps.
Plugin Claude Code
Plugin marketplace listing 1 plugin: ps.
Plugin Claude Code
Prompt quality management with agents, hooks, and MCP integration. Commands: /ps:r, /ps:a, /ps:lint, /ps:build, /ps:eval.
MCP server Claude CodeCodexCursor +2
MCP server "prompt-registry" as configured in joseph0926/prompt-shield. Runs ${CLAUDE_PLUGIN_ROOT}/servers/prompt-registry.js with node. Needs 1 environment variable to run.
Instructions file CodexOpenCode
Instructions for joseph0926/prompt-shield, covering promptshield agents, 에이전트 목록, gate-agent, lint-agent and registry-agent.
Instructions file
A set of instructions for PromptShield, a system for checking, storing, testing, and enforcing standards for prompts used with Claude Code and MCP tools.
Agent
Optimize prompts for clarity, coverage, and model reliability without changing intent.
Agent
Review prompts and provide actionable feedback for improvement.
Agent
Generate comprehensive test cases for prompts to validate output quality and consistency.
Command
Intercept Mode - Auto-improve and execute immediately.
Command
BUILD Mode - Design new prompts from requirements.
Command
EVAL Mode - Evaluate prompts with test datasets.
Command
Show prompt-shield usage guide and command reference.
Command
LINT Mode - Diagnose existing prompts with 8-Point Quality Check.
Command
Review Mode - Improve prompt and await approval before execution.
Hook
Runs when you submit a prompt, before the agent sees it, executing prompt-quality-check.sh. From joseph0926/prompt-shield.
Hook
Runs after a tool call finishes for Write and Edit tool calls, executing post-tool-check.sh. From joseph0926/prompt-shield.
Hook
Runs when a session starts, executing session-start.sh. From joseph0926/prompt-shield.
Skill Claude CodeCodex
A prompt-quality skill helps inspect, improve, design, and test instructions given to AI systems. It includes commands for reviewing, rewriting, checking, building, and evaluating prompts.