Anthropic Claude Pro/Max OAuth compatibility workflow for this repo. Use when debugging Anthropic OAuth failures, misleading extra-usage errors, Pi request shaping, prompt fingerprinting, or deciding between hook-based fixes and deeper provider overrides.
Review a module's dependency and structural patterns for code smells. Use when adding a parameter to a shared interface, when a dependency bag grows past 5 fields, or when planning a refactoring that touches wiring between layers.
Pi skill frontmatter reference and template. Use when creating or reviewing project skills so they conform to Pi's Agent Skills frontmatter rules, naming constraints, and description requirements.
Heuristics and process for discovering structural improvements in this package. Load when planning a new improvement round — contains the smell taxonomy, analysis workflow, and prioritization framework distilled from many phases of refactoring.
Project-specific markdown rules (one-sentence-per-line, compact tables, sequential numbering) and YAML frontmatter schema for plans/retros. Load when writing or editing markdown — contains rules that differ from standard markdownlint defaults.
Authoring and reviewing Mermaid diagrams — pitfall categories (semicolons, angle-bracket tokens, quoted headings), renderer verification, and state-machine disambiguation with note blocks. Load when authoring or reviewing Mermaid diagrams in any doc type.
Fast Pi CLI reproduction workflow for this repo. Use when debugging extension behavior through the real pi executable, especially for Anthropic OAuth failures, prompt shaping, request payload inspection, or validating changes without waiting on manual retries.
Reference for the Pi coding agent's turn/tool execution model and extension event lifecycle. Use when designing extension timing (when to flush, notify, or intercept), understanding event sequencing, or reasoning about what the agent sees between turns. Includes the verified lifecycle diagram, event handler…
Pre-completion protocol for implementation agents — gather context, dispatch the pre-completion-reviewer subagent, and handle its report before writing stage notes and recommending /ship-issue. Load at the end of /tdd-plan and /build-plan after all implementation steps are complete.
Tidy-First protocol for implementation agents — dispatch the tidy-first-assessor subagent over the files an upcoming change will touch, then triage its preparatory-refactor suggestions before implementing. Load at the start of /tdd-plan and /build-plan, after the green baseline is verified.
★not rated 227▲
+3 17d agoA66 tokens
originalMIT
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: