Agent Claude Code
Headless agent for CI pipelines. Runs tests, lint, and type checks; outputs a machine-readable CI PASS / CI FAIL summary. Invoke via claude -p "use the ci-reviewer agent" --output-format text in GitHub Actions.
Agent Claude Code
Use this agent to answer pricing comparison questions using only data already stored in test.db. It never scrapes; it only reads the database and produces structured comparisons. Use it when the user asks "compare X vs Y" or "what is the cheapest option for Z".
Command Claude Code
Argument: $ARGUMENTS (optional: "main" to deploy to main).
Command Claude Code
You must run your completed application and proof it's working.
Command Claude Code
Argument: $ARGUMENTS — the PR number or branch name to review.
Hook Claude Code
Runs before the agent uses a tool for Bash and Write tool calls, running an inline shell check (2 commands). From MissYueshuang/mcp-price-scout.
Hook Claude Code
Runs after a tool call finishes for Edit tool calls, running an inline shell check. From MissYueshuang/mcp-price-scout.
Hook Claude Code
Runs when the agent finishes a response, running an inline shell check. From MissYueshuang/mcp-price-scout.
Settings file Claude Code
Agent settings declaring 3 hook events (PreToolUse, PostToolUse, Stop) and 10 allowed tools.
Instructions file
Claude Code instructions for MissYueshuang/mcp-price-scout, covering pricescout — claude context, project purpose, architecture, key conventions and running the project.
MCP server Claude CodeCodexCursor +2
MCP server "pricescout" as configured in MissYueshuang/mcp-price-scout. Runs locally from the pricescout Python package.