Hook
Runs when you submit a prompt, before the agent sees it, executing skill-hint.sh and health-check.sh (2 commands). From rmzi/portable-dev-system.
Hook
Runs when you submit a prompt, before the agent sees it, executing skill-hint.sh and health-check.sh (2 commands). From rmzi/portable-dev-system.
Hook
Runs when a git worktree is created, executing sync-worktree-permissions.sh. From rmzi/portable-dev-system.
Hook
Runs when a git worktree is removed, executing remove-agent-worktree.sh. From rmzi/portable-dev-system.
Skill Claude CodeCodex
Fixing bugs using a test-first disciplined loop. Use when a bug is reported or discovered and needs a verified fix with minimal blast radius.
Skill Claude CodeCodex
Bumping project version and updating changelog atomically. Use when releasing a new version — patch, minor, or major.
Skill Claude CodeCodex
Save a checkpoint — bump version, commit, push. Use when work is complete and ready to ship without the full finish protocol.
Skill Claude CodeCodex
Contributing changes to PDS skills, agents, or workflow. Use before modifying any PDS artifact to follow the whitepaper-alignment checklist.
Skill Claude CodeCodex
Grounding in core development principles. Use when starting significant work, feeling stuck, or needing to reset decision-making clarity.
Skill Claude CodeCodex
Testing whether skills produce correct agent behavior. Use after modifying a skill, during periodic review, or when model upgrades may affect skill relevance.
Skill Claude CodeCodex
Structural codebase exploration using the codebase-memory-mcp SQLite index when one exists for the current project. Prefer over blind Grep when available.
Skill Claude CodeCodex
Export a Claude Code session to human-readable markdown. Use when the user wants to save, review, or share a conversation transcript.
Skill Claude CodeCodex
Completing a development branch for merge readiness. Use when implementation and tests pass and the branch needs formal preparation for review and merge.
Skill Claude CodeCodex
Interrogating requirements to validate before building. Use before swarm decomposition, design decisions on ambiguous features, or when scope creep risk is high.
Skill Claude CodeCodex
Recording, reviewing, and promoting engineering patterns. Use when observing a recurring pattern, during post-swarm analysis, or when an instinct reaches promotion threshold.
Skill Claude CodeCodex
Save session state and pause gracefully. Use when stopping work mid-session to preserve context for later resumption.
Skill Claude CodeCodex
Address PR review comments systematically. Use when a PR has review feedback that needs to be resolved with code changes.
Skill Claude CodeCodex
Focused rebase against a target branch. Use when you need to update a feature branch with upstream changes. Stops on conflicts — does not auto-resolve. Extended mode adds autonomous conflict resolution and test-fix loop.
Skill Claude CodeCodex
Reconstruct swarm state after a pause, a crash, or a handoff to a different machine or person. Use when starting a session that should continue prior swarm work instead of starting fresh.
Skill Claude CodeCodex
Launching multi-agent parallel work with the Agentic SDLC. Use when a task benefits from decomposition into parallel subtasks.
Skill Claude CodeCodex
Referencing the agent roster, roles, coordination model, and dispatch modes. Use when spawning agents or checking permissions.
Skill Claude CodeCodex
Associate every PDS task with a GitHub issue. Orchestrator finds or creates the ticket, posts plan and acceptance criteria as a checkbox list, updates it as work progresses. Use at Phase 1 of every swarm.
Skill Claude CodeCodex
Triage insights into actionable GitHub issues across repos. Use after running /insights to convert analysis into tracked work.
Skill Claude CodeCodex
Verifying work completeness before declaring done. Use before marking tasks complete, creating PRs, or claiming task status as done.
Skill Claude CodeCodex
Terse user-facing register — limited vocabulary, doubled state-transition phrases, no hedging or editorializing. Use in the top-level conversation and for orchestrator user-facing inline status only.