ralph-start
25Command Claude Code
Start a Ralph Loop for autonomous task completion.
Command Claude Code
Start a Ralph Loop for autonomous task completion.
Command Claude Code
Run a structured retrospective for the current session. Proposes rule and documentation changes but does not apply them.
Command Claude Code
Resolve a circuit breaker in the review loop. Accepts exactly one argument: approve, reject, or retry.
Command Claude Code
Submit work for peer review. Validates clean worktree, initializes or continues the review loop, invokes review-round-runner.sh, and returns the verdict.
Command Claude Code
Shape a rough idea into a Shape-Up pitch via the pitch-shaper agent.
Hook Claude Code
Runs before the agent uses a tool for Edit, Write and Bash tool calls, executing protect-files.sh and protect-git.sh (2 commands). From gosha70/code-copilot-team.
Hook Claude Code
Runs when the agent finishes a response, executing verify-on-stop.sh and peer-review-on-stop.sh (2 commands). From gosha70/code-copilot-team.
Hook Claude Code
Runs after a tool call finishes for Edit and Write tool calls, executing verify-after-edit.sh and auto-format.sh (2 commands). From gosha70/code-copilot-team.
Hook Claude Code
Runs when the agent sends a notification, executing notify.sh. From gosha70/code-copilot-team.
Hook Claude Code
Runs when a session starts, executing reinject-context.sh and memkernel-recall.sh (2 commands). From gosha70/code-copilot-team.
Hook Claude Code
Runs before the context is compacted, executing memkernel-pre-compact.sh. From gosha70/code-copilot-team.
Hook Claude Code
Runs after the context is compacted, executing memkernel-post-compact.sh. From gosha70/code-copilot-team.
Settings file Claude Code
Agent settings declaring 7 hook events (PreToolUse, Stop, PostToolUse, Notification) and 8 allowed tools.
Plugin Claude Code
Code Copilot Team hooks: file protection, auto-format, type verification, context re-injection, git safety, and desktop notifications.
Skill Claude CodeCodex
Produces implementation plans with files, interfaces, test strategy, and task breakdown. No code changes.
Skill Claude CodeCodex
Explores codebase, reads docs, searches the web. No code changes. Returns a research summary with paths, patterns, and risks.
Skill Claude CodeCodex
Holistic review of all changes — correctness, consistency, style, test coverage. Runs tests, checks console, verifies integration. Returns pass/fail report.
Skill Claude CodeCodex
Runs end-to-end verification of the project. Executes test suite, type checker, linter, and dev server. Reports pass/fail with specific failure details.
Cursor rule Cursor
Multi-agent delegation rules, three-phase workflow (Plan/Build/Review), model selection, collaboration gates, and Ralph Loop integration.
Cursor rule Cursor
Autonomous build driver after SDD spec approval: phase-scoped headless build sessions, driver-owned commits, cross-provider review gates, milestone pauses, and fail-closed escalation — under explicit opt-in autonomy profiles.
Cursor rule Cursor
When and how to ask clarifying questions before implementing. Data model review gate and ambiguity resolution rules.
Cursor rule Cursor
Quality gates, prohibited patterns, verification discipline, and self-audit rules for all code generation and review sessions.
Cursor rule Cursor
Cross-copilot portable conventions: target alignment, complexity control, minimal changes, git discipline, and project structure.
Cursor rule Cursor
Copyright header rules for generated source files. Applies the company name from providers.toml to new files.