pbdeuchler

Use when reviewing a completed implementation holistically - a finished branch, a completed plan step, or a diff before PR. Reviews every changed line against the implementation plan (if one exists) and high engineering standards across seven dimensions, verifies tests by deliberately breaking crucial code, and emits severity-classified findings with a PASS/FAIL verdict.

Use when performing a holistic code review of an implementation - routes to codex:rescue or falls back to a direct subagent, both running the house-style:holistic-review skill

ALWAYS use before any implementation work, review, or planning: designing, writing, editing, refactoring, debugging, reviewing, or generating source code, tests, scripts, config-as-code, or behavior-affecting files. This is a baseline engineering skill and should be invoked even when a more specific language, framework, testing, or database skill also applies.

Use when asked to write, draft, file, or open a GitHub issue - mandates exploring the relevant code to understand the whole problem space, reasoning any proposed solution, and structuring the issue with summary, what/why, references, nuances, open questions, and acceptance criteria. Adds professionalism and no-sensitive-info discipline for public repos.

Use when creating, editing, triaging, or cleaning up GitHub issues - a mechanical pass that verifies the title is accurate and current, labels/assignees/milestone are correct, and the body is valid, well-formed markdown, all via the gh CLI. Does not judge content quality.

Use when running Python, installing Python packages, creating virtualenvs, or executing Python CLI tools - mandates uv/uvx over direct python/pip/pipx/venv calls when uv is installed, and gives the drop-in command mappings

Use when the user provides a reference implementation (URL, repo path, branch, file) plus a verb like "use", "copy", "adapt", "port", "model after" - mandates fetching/reading the reference before designing, and lifting the structure rather than reimagining it.

Use when adding or modifying non-trivial code - requires happy-path AND sad-path tests covering every return permutation, blocks declaring "done" if production code grew without matching test additions.

Use when building, explaining, testing, or modifying Rust agent harnesses with the Halter library. Applies to simple one-shot runners, chat sessions, embedded services, custom tools, hook policy, skills/plugins, subagents, persistence, provider configuration, event consumers, and Halter workspace Rust changes.

Use when building scripted, deterministic multi-agent workflows in Rust on top of the Halter SDK. Applies to fan-out/fan-in (map-reduce), staged pipelines, adversarial verification, judge panels, produce-review-repair loops, loop-until-count / loop-until-dry / loop-until-budget loops, multi-modal sweeps, structured agent output, side-effect isolation, concurrency control, token budgeting, progress reporting, and resumable orchestration. Pairs with the basic-rust skill, which covers harness construction.