Plugin Claude Code
Core planning and workflow infrastructure for the Claudikins ecosystem.
Plugin Claude Code
Core planning and workflow infrastructure for the Claudikins ecosystem.
Agent
Agent "babyclaude" from povvo/claudikins-kernel, covering babyclaude, your task, acceptance criteria, core principle and what you do.
Agent
Output verification agent for /claudikins-kernel:verify command. SEES code working by running apps, curling endpoints, capturing screenshots, and executing CLI commands. This is the feedback loop that makes Claude's code actually work. Use this agent during /claudikins-kernel:verify Phase 2 to gather evidence that…
Agent
Code quality reviewer for /claudikins-kernel:execute command. Reviews code quality, patterns, and maintainability. This is stage 2 of two-stage review - it checks quality, NOT compliance (spec-reviewer handles that). Use this agent after spec-reviewer passes. The agent receives the implementation diff and reviews for…
Agent
Merge conflict resolution agent for /claudikins-kernel:execute command. Analyses git merge conflicts and proposes resolutions. Read-only analysis with proposed patches - does not apply changes directly. Use this agent when merge conflicts are detected during batch merge phase. The agent examines both sides of the…
Agent
Code simplification agent for /claudikins-kernel:verify command. Performs an optional polish pass after verification succeeds. Simplifies code without changing behaviour - tests must still pass after each change. Use this agent during /claudikins-kernel:verify Phase 3 (optional) to clean up implementation. The agent…
Agent
Documentation perfectionist for /claudikins-kernel:ship command. Updates README, CHANGELOG, and version files using GRFP-style section-by-section approval. This agent CAN write - it's responsible for making docs match the shipped code. Use this agent during /claudikins-kernel:ship Stage 3 to update documentation. The…
Agent
Specification compliance reviewer for /claudikins-kernel:execute command. Verifies implementation matches the plan spec. This is stage 1 of two-stage review - it checks compliance, NOT quality. Use this agent after babyclaude completes a task, before code-reviewer. The agent receives task description, acceptance…
Agent
Research agent for /claudikins-kernel:outline command. Explores codebase, documentation, or external sources to gather context before planning decisions. This agent is READ-ONLY - it cannot modify files. Use this agent when you need to research before making planning decisions. Spawn 2-3 instances in parallel with…
Command
Execute validated plans with isolated agents and two-stage review.
Command
Iterative planning with human checkpoints at every phase.
Command
Final shipping gate. PR creation, documentation updates, and merge with human approval.
Command
Post-execution verification gate. Tests, lint, type-check, then see it working.
Hook
Runs when a session starts on claudikins-kernel:verify and claudikins-kernel:ship, executing session-startup.sh, verify-init.sh and ship-init.sh (3 commands). From povvo/claudikins-kernel.
Hook
Runs when you submit a prompt, before the agent sees it for claudikins-kernel:execute, claudikins-kernel:execute.*(--status and status) tool calls, executing skill-activation-hook.sh, validate-plan-format.sh and execute-status.sh (3 commands). From povvo/claudikins-kernel.
Hook
Runs when a subagent starts for babyclaude tool calls, executing trace-start.sh and create-task-branch.sh (2 commands). From povvo/claudikins-kernel.
Hook
Runs when a subagent finishes, executing trace-end.sh. From povvo/claudikins-kernel.
Hook
Runs before the agent uses a tool for Bash and Task tool calls, executing git-branch-guard.sh, sanitize-bash.sh, merge-gate.sh and pre-task-gate.sh (4 commands). From povvo/claudikins-kernel.
Hook
Runs after a tool call finishes for Edit and Write tool calls, executing autoformat.sh and execute-tracker.sh (2 commands). From povvo/claudikins-kernel.
Hook
Runs when the agent finishes a response for claudikins-kernel:verify, claudikins-kernel:ship, claudikins-kernel:outline and claudikins-kernel:execute tool calls, executing verify-gate.sh, ship-complete.sh, validate-plan-completion.sh and batch-checkpoint-gate.sh (4 commands). From povvo/claudikins-kernel.
Hook
Runs before the context is compacted, executing preserve-state.sh. From povvo/claudikins-kernel.
Skill Claude CodeCodex
Use when running claudikins-kernel:outline, brainstorming implementation approaches, gathering requirements iteratively, structuring complex technical plans, or facing analysis paralysis with too many options — provides iterative human-in-the-loop planning with explicit checkpoints and trade-off presentation.
Skill Claude CodeCodex
Use when running claudikins-kernel:execute, decomposing plans into tasks, setting up two-stage review, deciding batch sizes, or handling stuck agents — enforces isolation, verification, and human checkpoints; prevents runaway parallelization and context death.
Skill Claude CodeCodex
Use when running claudikins-kernel:ship, preparing PRs, writing changelogs, deciding merge strategy, or handling CI failures — enforces GRFP-style iterative approval, code integrity validation, and human-gated merges.