Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/cyrus123456/orca/agents-mdgit clone --depth 1 https://github.com/cyrus123456/orcaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/cyrus123456/orca/agents-md)<a href="https://agentmods.dev/instructions/cyrus123456/orca/agents-md"><img src="https://agentmods.dev/badge/instructions/cyrus123456/orca/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.03332 | $0.03332 |
| Opus 5 | $0.01666 | $0.01666 |
| Sonnet 5 | $0.00666 | $0.00666 |
| Haiku 4.5 | $0.00333 | $0.00333 |
Grade A, and why
orca AGENTS.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Windows child processes**: start them through `runProcess`/`spawnProcess` in `src/shared/child-process/` — never `child_process` directly. It pins `windowsHide`, refuses `shell: true`, and encodes `.cmd`/`.bat` argum How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[全局规则引用] c:\Users\73476.config\opencode\AGENTS.md
Project Overview
Orca is an Electron desktop app that orchestrates CLI coding agents (Claude Code, Codex, OpenCode, etc.) across parallel git worktrees. It also has a mobile companion app (React Native/Expo) and a CLI (orca).
Stack: Electron 43 + electron-vite, React 19, Tailwind v4, shadcn (new-york-v4), zustand, vitest, oxlint, TypeScript 7
Runtime: Node 24, pnpm 10.24
Developer Commands
pnpm install # install deps (also runs postinstall: rebuild native deps)
pnpm dev # start Electron dev server (runs ensure:electron-runtime first)
pnpm dev:web # web-only dev server (no Electron)
# Verification — run in this order before PRs:
pnpm lint # oxlint + switch-exhaustiveness + styled-scrollbars + reliability-gates + max-lines-ratchet + skill/localization checks
pnpm typecheck # runs all 3: node + cli + web
pnpm test # vitest run (config/vitest.config.ts)
pnpm build # full desktop build (typecheck → relay → cli → electron-vite → web → native)
# Focused commands:
pnpm typecheck:node # main + preload + shared + relay + types
pnpm typecheck:cli # CLI-specific
pnpm typecheck:web # renderer + shared
pnpm test:e2e # Playwright e2e (requires Electron runtime)
pnpm format # oxfmt --write .
Mobile app (separate workspace in mobile/):
cd mobile && pnpm install && pnpm start # Expo dev server
cd mobile && pnpm test # vitest run
Architecture
src/
main/ Electron main process (IPC, git, SSH, terminals, daemon, agent integrations)
preload/ Electron preload (bridge API types — NO .d.ts files allowed here)
renderer/ React UI (src/renderer/src/) — see path aliases below
shared/ Code imported by both main and renderer (NO .d.ts files allowed here)
relay/ WebSocket relay for SSH/remote worktree sessions
cli/ `orca` CLI entrypoint and command handlers
types/ Build-constant ambient declarations (only .d.ts allowed here)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · +7 lines · +235 tokens per session 82f310f9d001
- 3d ago First seen · 173 lines · 3,097 tokens per session scan A 9a5ffdad63d4
orca AGENTS.md is an instructions file published in the GitHub repository cyrus123456/orca (0 stars, last pushed today), licensed MIT. It adds 3,332 tokens to every session, about $0.0167 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). It comes from a forked repository.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.