Report · marked 8 Oct 2026

stablyai/orca

Solid foundations, held back in a few specific places.

TypeScript · 87,896 stars · 34,809 files · branch main

79 /100 A-

Instructions 27/27Whether the repo tells an agent how to behave before it starts guessing. Full marks.Setup 14/20Whether an agent can install the project and get it running without a human. Losing marks on environment config and reproducible environment.Verification loop 21/25Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy. Losing marks on lint and format rules and static type checking.Context economy 9/20Whether the repo fits in a context window, or fights it. Losing marks on file sizes fit in context and repository weight.Navigability 10/10How quickly anything new can orient itself. Full marks.

Higher is better. Accent marks what is costing you most.

Fix these first

File sizes fit in context

A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.

Environment config

Add a .env.example listing every variable with a safe placeholder value. It's the cheapest possible fix and it unblocks the whole first run.

Repository weight

Large binaries and vendored trees slow every operation an agent performs. Git LFS or a separate assets repo keeps the working tree navigable.

The full marking

Every deduction below names the file or setting it came from.

Instructions 27/27 A+

Whether the repo tells an agent how to behave before it starts guessing.

✓Agent instruction file 12/12

AGENTS.md is present, which is the format the most tools read.

Also found: CLAUDE.md

✓Instruction quality 12/12

Specific enough that an agent can act on it.

12,043 characters, a workable length

names the actual commands to run

uses headings, so an agent can skim it

includes copyable code blocks

✓README as an entry point 3/3

README has a clear getting-started section.

Setup 14/20 B+

Whether an agent can install the project and get it running without a human.

✓Deterministic install 6/6

pnpm-lock.yaml pins the dependency tree.

Found pnpm-lock.yaml

✓Discoverable commands 6/6

Commands are declared where an agent will look for them.

package.json scripts (install:release, audit:perf, test:perf:contracts, format, lint, audit:code-quality…)

✗Environment config 0/4

Nothing documents the environment this needs. An agent will get a runtime error it can't diagnose.

Add a .env.example listing every variable with a safe placeholder value. It's the cheapest possible fix and it unblocks the whole first run.

✓Pinned runtime version 2/2

The language runtime version is pinned.

package.json engines.node 24

✗Reproducible environment 0/2

No container or devcontainer definition.

A Dockerfile or devcontainer removes an entire class of 'it won't install' failures.

Verification loop 21/25 A-

Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy.

✓Tests exist 8/8

14344 test files against 32492 source files.

e.g. .github/actions/cloud-sql-rollout-lease/action-contract.test.mjs, .github/actions/cloud-sql-rollout-lease/storage-lease.test.mjs, cloud/apps/push/src/apns-client.test.ts

✓Test command is discoverable 7/7

An agent can find and run `npm run test`.

✓Continuous integration 4/4

82 GitHub Actions workflows define what "passing" means.

✗Lint and format rules 0/3

No linter or formatter config. Style is tribal knowledge, so agent output will drift from yours.

A formatter config is the cheapest way to stop reviewing whitespace in agent diffs. It moves style from opinion to a command.

✗Static type checking 2/3

Type checking is configured, but not in strict mode.

Turn on `"strict": true`. Type errors are the fastest feedback an agent gets, and non-strict mode silently discards most of them.

Context economy 9/20 C

Whether the repo fits in a context window, or fights it.

✓No committed build output 6/6

No generated directories committed.

✓.gitignore hygiene 3/3

.gitignore covers 103 patterns.

✗File sizes fit in context 0/6

10 source files are over 100KB.

A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.

cloud/apps/relay/src/assignment-store.ts — 362KB

src/cli/bundled-skill-guides.ts — 293KB

native/computer-use-macos/Sources/OrcaComputerUseMacOS/main.swift — 167KB

✗Repository weight 0/5

About 1271MB checked out. Large enough that cloning and searching are both slow.

Large binaries and vendored trees slow every operation an agent performs. Git LFS or a separate assets repo keeps the working tree navigable.

Here is your AGENTS.md

Drafted from what is actually in this repository: the install command from your lockfile, the commands you already declare, your real directory layout. Anything marked TODO needs a person. Save it at the root as AGENTS.md.

AGENTS.md — drafted for stablyai/orca

# AGENTS.md

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

## Setup

```
pnpm install
```

## Commands

```
pnpm dev               # run locally
pnpm start             # run the app
pnpm build             # produce a build
pnpm test              # run the test suite, must pass before any commit
pnpm typecheck         # type check without emitting
pnpm lint              # lint
pnpm format            # format
pnpm install:release
```

## Layout

- `src/`    27302 source files
- `mobile/` 2701 source files
- `tests/`  973 source files
- `config/` 844 source files
- `cloud/`  475 source files
- `docs/`   137 source files

## Conventions

- Tests live alongside the code they cover, following `.github/actions/cloud-sql-rollout-lease/action-contract.test.mjs`.
- TypeScript is not in strict mode. Turning it on catches a whole class of mistakes before they run.
- CI defines what passing means. See `.github/workflows/adhoc-mac-build.yml`, and keep it green.
- TODO: add the two or three conventions a newcomer always gets wrong here.

## Gotchas

- `cloud/apps/relay/src/assignment-store.ts` is 362KB. It will not fit comfortably in context, so read it in parts.

---

Drafted by agentreadme.com from what is in this repository. Everything marked TODO
needs a human. Check it in as AGENTS.md at the root.

Open the raw markdown or curl -o AGENTS.md agentreadme.com/draft/stablyai/orca.md

A draft gets the commands right and stops at the things only a maintainer knows. What a good TypeScript AGENTS.md looks like covers what to add by hand, and what AGENTS.md is explains the format itself.

Show the mark

The badge re-checks daily, so it keeps up as the repository changes. Use mark again to force it now.

[![agent ready](https://agentreadme.com/badge/stablyai/orca.svg)](https://agentreadme.com/stablyai/orca)

Other TypeScript repositories, marked

freeCodeCamp/freeCodeCamp 69 B openclaw/openclaw 73 B+ nilbuild/developer-roadmap 45 C deepseek-ai/deepseek-harness 82 A- vuejs/vue 67 B anomalyco/opencode 78 A-

All TypeScript repositories

Think this mark is wrong?

Every deduction above names the file it came from, so this can be settled by looking. If a check missed something, that is a rule worth fixing.

Open an issue, already filled in