Sanitized open-source Pi agent configuration, skills, and extensions
This repository also configures its own agents. See what agent-public tells them →
Skill Claude CodeCodex
Orchestrate the full atelier workflow in one task window using pi teams runtime teams plus predefined agents, spawning right-side worker panes only when a phase is active and routing review loops until acceptance while preserving planner/implementer live context. Use when running…
Skill Claude CodeCodex
Compare 2-3 materially different child-level contract/interface shapes and write the chosen direction into CONTRACTDECISION.md before planning when local contract shape is ambiguous.
Skill Claude CodeCodex
Compare 2-3 materially different initiative decompositions in SPLITOPTIONS.md when task boundaries or sequencing are still ambiguous before authoring TASKGRAPH.md.
Skill Claude CodeCodex
Mine the current chat/history for forgotten durable-residue candidates and backfill .plans/ /ARTIFACTCANDIDATES.md without touching tracked AGENTS.md. Use when implementation/debugging ran long, candidate capture was likely missed, or a human wants a manual mid-task history harvest.
Skill Claude CodeCodex
Create a parent initiative packet under .initiatives/ / with the canonical file tree, seeded shared-context docs, placeholder-owned files, and initial routing fields before split work begins.
Skill Claude CodeCodex
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree one decision at a time. Use when a task is under-specified, a design needs stress-testing, or the user asks to be grilled.
Skill Claude CodeCodex
Create an initiative child task packet in the selected child row's Packet Root at .plans/ / with imported context, placeholder plan ownership, and packet-phase bootstrap metadata before planning begins.
Skill Claude CodeCodex
Implement a planned task from .plans/ / with strict plan adherence, explicit amendments, and no direct writes to tracked AGENTS.md.
Skill Claude CodeCodex
Plan a development task into a self-sufficient execution contract stored in .plans/ / for later fresh-context implementation and review.
Skill Claude CodeCodex
Audit the tracked AGENTS.md tree against best practices, write .agents/AGENTSTREEREVIEW.md, and propose cleanup, compaction, conflict resolution, or sharding when needed. May auto-apply only trivial non-semantic hygiene fixes.
Skill Claude CodeCodex
Review implementation for maintainability, evolvability, anti-slop, and human complexity; emit M# findings and durable residue candidates when needed.
Skill Claude CodeCodex
Blind-review TASKGRAPH.md and optional SPLITOPTIONS.md, then write SPLITREVIEW.md with a ready/notready verdict before any child packets are hydrated.
Skill Claude CodeCodex
Review PLAN.md as a blind-handoff execution contract; emit P# findings into the task packet and block plans with ambiguity, hidden assumptions, poor artifact hygiene, or missed durable-residue calls.
Skill Claude CodeCodex
Turn a framed initiative into a reviewed child-task graph in TASKGRAPH.md, using vertical slices, explicit dependencies, canonical child statuses, and reviewable child boundaries.
Skill Claude CodeCodex
Populate UBIQUITOUSLANGUAGE.md inside an initiative packet with canonical terms, aliases to avoid, flagged ambiguities, and term relationships before decomposition hardens.
Skill Claude CodeCodex
Fold a child loop back into the parent initiative packet, update canonical parent truth, record the sync log, and route the next durable-distill timing decision.
Skill Claude Code
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
Skill Claude CodeCodex
Implement development tasks in safe, reviewable increments. Use when the user wants code changes executed with clear sequencing, validation, maintainability guardrails, and alignment with later code review.
Skill Claude CodeCodex
Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more AI-navigable.
Skill Claude CodeCodex
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
Skill Claude CodeCodex
Triage a bug or issue by exploring the codebase to find root cause, then write an issue document in a local .issues folder with a TDD-based fix plan. Use when user reports a bug, wants to file an issue, mentions "triage", or wants to investigate and plan a fix for a problem.
Skill Claude CodeCodex
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
Skill Claude Code
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include…
Skill Claude CodeCodex
Create focused GitLab merge requests with glab. Use when code changes are already implemented in a Git repository and Codex needs to inspect git state, isolate only the intended files, create or reuse a feature branch, run the repo's required validation commands, commit cleanly, push to origin, and open a merge…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: