Agent Claude Code
Review Python runner code for convention violations. Use after modifying files under components/runners/ambient-runner/. Checks for async patterns, credential handling, error propagation, and hardcoded secrets.
Agent Claude Code
Cross-cutting security review for code touching auth, RBAC, tokens, or container specs. Use before committing any code that handles authentication, authorization, credentials, or security contexts.
Command Claude Code
Log a new Jira issue to RHOAIENG with Team (Ambient team) and Component (Agentic) pre-filled.
Skill Claude CodeCodex
Use when creating or updating Gerrit changes — pushing code for review, amending patch sets, setting reviewers and topics. Triggers on "push to Gerrit", "create a Gerrit change", "upload for review", "update the patch set", "add reviewers to this change".
Skill Claude CodeCodex
Use when reviewing a Gerrit change — fetching change details, reading diffs, posting inline comments, and voting with labels. Triggers on "review this Gerrit change", "review change 12345", "look at this Gerrit CL", "code review on Gerrit".
Skill Claude CodeCodex
Use when submitting or preparing a Gerrit change for merge — checking submit requirements, rebasing, resolving comments, and submitting. Triggers on "submit this Gerrit change", "merge this CL", "is this change ready to submit", "check submit requirements".
Hook Claude Code
Runs before the agent uses a tool for Bash, Edit and Write tool calls, executing pr-review-gate.sh and convention-guard.sh with --show-toplevel (2 commands). From ambient-code/platform.
Hook Claude Code
Runs after a tool call finishes for Edit, Write and Bash tool calls, executing auto-format.sh and coderabbit-review-gate.sh with --show-toplevel (2 commands). From ambient-code/platform.
Hook Claude Code
Runs when the agent finishes a response, executing stop-review.sh with --show-toplevel. From ambient-code/platform.
Settings file Claude Code
Agent settings declaring 3 hook events (PreToolUse, PostToolUse, Stop).
MCP server Claude CodeCodexCursor +2
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.
MCP server Claude CodeCodexCursor +2
Lets the agent read DeepWiki's AI-generated documentation of any public GitHub repository and ask questions about a codebase. Runs locally from the deepwiki-mcp npm package.
Instructions file CodexOpenCode
Instructions for ambient-code/platform, a project described as: Vision/Mission https://ambient-code.ai : Virtual team management and collaboration platform. User guides: https://ambient-code.github.io/platform/.
Instructions file
Instructions for ambient-code/platform, covering ambient code platform, structure, key files, session flow and commands.
Command Claude Code
Start a fresh PostgreSQL container and run all migrations. If a database already exists, this will tear it down first.
Command Claude Code
Add a new field to an existing Kind, updating all layers consistently.
Command Claude Code
Generate a complete CRUD entity (Kind) using the automated generator script.
Command Claude Code
Completely remove a generated Kind and all its artifacts from the project.
Command Claude Code
Regenerate the Go client code from OpenAPI specifications. Run this after modifying any openapi/.yaml files.
Command Claude Code
Validate that this TRex-spawned project is in a healthy, working state. This command is idempotent — it succeeds if everything is already running and correct, and only fails if something is genuinely broken.
Command Claude Code
Build and start the API server with authentication and authorization disabled for local development.
Command Claude Code
Run integration tests against a real PostgreSQL database (provisioned automatically via testcontainers).
Command Claude Code
Run unit tests against the package and command code (no database required).
Command Claude Code
Run all static analysis checks: go vet, format verification, and linting.