Skill Claude CodeCodex
Initialize a new project with the Coograph template — auto-detect tech stack, fill all TBD placeholders, optionally set up the code-graph. Trigger when the user types /coograph-init or $coograph-init, asks to "initialize the project", "set up coograph", "wire up coograph", "add coograph to this repo", or otherwise…
Command Claude Code
Diagnose the bug or build error below. Find the root cause with minimal investigation, then apply the smallest possible fix.
Command Claude Code
Initialize a new project with this Coograph template. Interactive setup that auto-detects the tech stack and fills all placeholders.
Command Claude Code
Start work on a new ticket below. Run pre-flight checks, investigate the codebase, and flow into an OpenSpec proposal.
Command Claude Code
You are an interview-driven planner. Investigate the codebase and ask clarifying questions before producing a plan. You plan — you never implement.
Command Claude Code
Review the changes in scope for spec compliance, convention violations, logic bugs, and architectural issues. You review — you do not author. Never edit files.
Command Claude Code
Fast read-only codebase search and Q&A. Answer the question below with evidence. You explore — you do not edit files or implement changes.
Command Claude Code
Verify that the described work is complete and correct. Provide evidence for every claim. You verify — you do not implement or fix style.
Hook Claude Code
Runs when a session starts, executing report-graph.py via python3. From paullukic/coograph.
Hook Claude Code
Runs before the agent uses a tool for Bash, Edit, Write, MultiEdit and NotebookEdit tool calls, executing log-bash.py, block-generated.py and warn-scope.py via python3 (3 commands). From paullukic/coograph.
Settings file Claude Code
Agent settings declaring 2 hook events (SessionStart, PreToolUse).
Agent
Root-cause analysis, regression isolation, and build error resolution with minimal fixes.
Agent
Fast read-only codebase exploration and Q&A subagent. Prefer over manually chaining multiple search and file-reading operations to avoid cluttering the main conversation. Safe to call in parallel. Specify thoroughness: quick, medium, or thorough.
Agent
Interview-driven planning that produces actionable work plans with acceptance criteria.
Agent
Reviews changes against project conventions, specs, and testing standards.
Agent
Evidence-based completion checks — runs tests, checks diagnostics, validates acceptance criteria.
Instructions file GitHub Copilot
Instructions for paullukic/coograph, covering copilot instructions, pre-flight (run on every session start), mindset, communication style and default tone.
Instructions file GitHub Copilot
Global communication style — applies to all workspaces and conversations.
Instructions file GitHub Copilot
Conventions for CSS/styling files — loaded only when editing styles.
Instructions file GitHub Copilot
Conventions for test files — loaded only when editing tests.
Skill Claude CodeCodex
Implement tasks from an OpenSpec change. Use when the user wants to start or continue implementing a proposed change.
Skill Claude CodeCodex
Archive a completed change. Use when implementation is done and the change is ready to be moved to the archive.
Skill Claude CodeCodex
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
Skill Claude CodeCodex
Start work on a new ticket. Runs pre-flight checks, investigates the codebase, and flows into OpenSpec proposal. Use when the user pastes a ticket, issue, or task description.