AGENTS.md · stablyai/orca
AGENTS.md from stablyai/orca: 70 lines covering Reuse Before Reimplementing, Avoid Comments, File and Module Naming, Type Assertions: Prefer Checked Types and…
Template by stablyai
Install
Works with Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Claude Code. Read the repository before you give any tool access to your data.
curl -fsSL https://raw.githubusercontent.com/stablyai/orca/main/AGENTS.md -o AGENTS.md
Read it and adapt it to your project before use.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: prompt-engineering
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
What's in it
An AGENTS.md file: instructions coding agents (Codex, Cursor, Copilot, Gemini CLI and others) read before working in a repo.
- For
- Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Claude Code
- Length
- 70 lines
- File
AGENTS.md
Sections
- Reuse Before Reimplementing
- Avoid Comments
- File and Module Naming
- Type Assertions: Prefer Checked Types
- Cross-Platform Support
- Remote Use Case
- Mobile
- Folder Workspaces
First lines (shown under the repo's MIT license)
# Useful Commands - **Before handoff**: `pnpm check:changed --maxWorkers=2` (format, lint, typecheck, affected tests, ratchets; cached when nothing changed) - **Typecheck**: `pnpm tc` (or `tc:node` / `tc:cli` / `tc:web`) - **Test**: `pnpm test [path/to/file.test.ts]`; affected only: `pnpm test:changed [path] --maxWorkers=2` ([details](.github/CONTRIBUTING.md#targeting-local-tests)) - **Lint**: `oxlint`; format: `pnpm format` # Ensure main is always releasable Never break main. Use stacks or collapse PRs before merge # Design System All UI work — layout, color, typography, spacing, component selection, UX behavior — must follow [`docs/STYLEGUIDE.md`](./docs/STYLEGUIDE.md). Use the tokens defined in `src/renderer/src/assets/main.css` (the canonical source) and the shadcn primitives in `src/renderer/src/components/ui/`. Don't invent new color values, font sizes, or shadow tiers when a documented one already covers the role. Read the `docs/styleguide/` deep dive it links only when your change touches that topic. When STYLEGUIDE.md is silent, follow the resolution order in its final section. # Electron UI Validation Always run tests and agent-launched apps in the background with `ORCA_BACKGROUND_LAUNCH=1`. Never steal monitor focus or reveal test windows: no `show()`, `showInactive()`, `bringToFront()`, `app.focus()`, or OS activation. Use CDP screenshots of hidden renderers. Keep native-focus and visible-window tests paused on the user's desktop; run them on an isolated display or CI. Rebuild modified launch-policy code before running an app; stale build wrappers are not safe. Use the `$electron` skill and Playwright CDP for rendered Orca UI checks. Do not use computer-use for Orca UI validation. Screenshot presentational components without Electron: `pnpm fixtures:shot <id>` ([fixtures](docs/agents-md-refs/component-fixtures.md)). # Code Style ## Reuse Before Reimplementing Before writing new logic at any scale — a function, component, IPC channel, state store, or whole subsystem/flow — check whether an existing implementation already does the job. Extend or generalize it instead of building a parallel version. ## Avoid Comments - Only use when code does not describe - BE CONCISE. 1 LINE if possible (why not how) ## File and Module Naming Never use vague names like `helpers`, `utils`, `common`, `misc`, or `shared-stuff` for files, folders, or modules. They carry zero info and tend to become dumping grounds. Name files after what they _actually_ contain — prefer the concrete domain concept (e.g. `tab-group-state.ts`, `terminal-orphan-cleanup.ts`) over the generic role (`tabs-helpers.ts`, `terminal-utils.ts`). If you find yourself reaching for `helpers`, the file probably has more than one responsibility and should be split, or there's a better name hiding in the code that describes what the functions operate on. ## Type Assertions: Prefer Checked Types Avoid type assertions except `as const`. Unavoidable casts need a line-specific `SAFETY:` explanation: # First Class Citizens Every change must consider these areas: ## Cross-Platform Support Support macOS, Linux, and Windows. Guard platform-specific behavior at runtime; use platform-aware shortcuts, paths, and existing process wrappers. Before changing platform-specific code, processes, shells, shortcuts, paths, or native modules, read [`docs/agents-md-refs/cross-platform-support.md`](./docs/agents-md-refs/cross-platform-support.md). ## Remote Use Case Support remote execution as well as local. Clients and servers update independently; preserve compatibility across mixed versions. ## Mobile Any feature should be considered for parity on mobile ## Folder Workspaces All changes must consider folder workspaces as well as git worktrees. Don't assume every workspace is a git worktree. # Git / GitHub If changing code around `git`, `gh`, source-control, or review behavior read [`docs/agents-md-refs/git-workflow.md`](./docs/agents-md-refs/git-workflow.md). For a failed GitHub Actions run, inspect the failed jobs and retry with `gh run rerun <run-id> --failed --repo stablyai/orca`. Preserve successful jobs; use a full rerun only when the failure requires revalidating them. A code fix needs a new push and fresh checks, not a retry of the old SHA. # Tests Avoid adding low-value tests. These might be fine for development but offer negative value when checked in. [Anti-patterns](./docs/agents-md-refs/test-antipatterns.md)
Signals
- Stars
- 104,555
- Forks
- 6,602
- Open issues
- 4,413
- Last commit (this folder)
- Oct 23, 2026 (5 days ago)
- Last release
- Oct 24, 2026 (4 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/stablyai/orca
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from stablyai
- 0.738score
orca
stablyai
Desktop and mobile app that runs several coding agents side by side, each in its own git worktree
AgentAFreshness: A★ 104.6K - 0.518score
repository-review
stablyai
Review a repository change for correctness, security, and maintainability.
SkillCFreshness: C★ 7Claude Code +9 - 0.515score
change-handoff
stablyai
Prepare a precise handoff for unfinished repository work.
SkillCFreshness: C★ 7Claude Code +9
Cite this page
AGENTS.md · stablyai/orca. Agent Mart. https://agentmart.dev/templates/stablyai-orca-agents-md (last updated 2026-10-24)