codewith

Optimize slow Rust test workflows in Codewith codex-rs. Use when tests feel slow, compile/link dominates execution, app-server integration tests are filtered but still build huge binaries, or when deciding local/CI test strategy, target dirs, nextest filters, or Codewith skill guidance for test speed.

Use when the user asks to merge a GitHub PR, merge when green, enable auto-merge, add to a merge queue, or decide whether a PR is mergeable. Do not use for ordinary PR review unless there is explicit merge intent.

Route and verify development work in the hasna/codewith fork across Rust runtime, provider/model/auth/profile behavior, TUI, app-server protocol, MCP lifecycle, goals/native loops, upstream merges, and release gates. Use when implementing, debugging, reviewing, or shipping work in any of these Codewith runtime domains, especially changes that cross crates or user-facing surfaces and need the correct project skills, focused tests, snapshots, schemas, or fork-preservation checks.

Build, format, lint, and test Codewith Rust crates in codex-rs. Use when making or verifying Rust changes, resolving Codewith build errors, updating Cargo or Bazel locks, building release binaries, or validating Rust before npm publish.

Diagnose and safely repair Codewith config.toml and MCP startup failures. Use only when the user explicitly starts the self-heal workflow or asks to fix Codewith configuration/MCP breakage.

Update the title and body of one or more pull requests.

Create logical commits and push Codewith changes safely. Use when asked to review current changes, split work into commits, avoid unrelated local work, push to GitHub, reconcile a dirty hasna/codewith checkout, or prepare commits before publishing.

Publish Codewith npm releases for the hasna/codewith fork. Use when Codewith needs to bump or verify release versions, package @hasna/codewith, publish to npm, update a local install, smoke-test the installed codewith command, or align rust-v* tags with the published commit.

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep watching open PRs so fresh review feedback is surfaced promptly. Use when the user asks Codewith to monitor a PR, watch CI, handle review comments, or keep an eye on failures and feedback on an open PR.

Model visible context

Test authoring guidance

Diagnose GitHub bug reports in openai/codex. Use when given a GitHub issue URL from openai/codex and asked to decide next steps such as verifying against the repo, requesting more info, or explaining why it is not a bug; follow any additional user-provided instructions.

Run a GitHub issue digest for openai/codex by feature-area labels, all areas, and configurable time windows. Use when asked to summarize recent Codewith bug reports or enhancement requests, especially for owner-specific labels such as tui, exec, app, or similar areas.

How to run tests using remote executor.

Guide for testing Codewith TUI interactively

Update Codewith's pinned `v8` / `rusty_v8` versions, validate the release-candidate path, and investigate failed V8 canary or artifact builds. Use when asked to bump V8, update `rusty_v8` artifacts, prepare or validate a V8 release candidate, check `v8-canary`, or diagnose why a V8 version update no longer builds.

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codewith should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.

Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains.

Create and scaffold plugin directories for Codewith with a required `.codex-plugin/plugin.json`, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codewith needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries for plugin ordering and availability metadata, or update an existing local plugin during development with the CLI-driven cachebuster and reinstall flow.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codewith's capabilities with specialized knowledge, workflows, or tool integrations.

Install Codewith skills into $CODEWITH_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).