Report · marked 25 Aug 2026
musistudio/claude-code-router
An agent can work here, but it will waste turns finding its footing.
TypeScript · 36,869 stars · 788 files · branch main
63
/100
B
Instructions
3/27Whether the repo tells an agent how to behave before it starts guessing. Losing marks on agent instruction file and instruction quality.Setup
16/20Whether an agent can install the project and get it running without a human. Losing marks on environment config.Verification loop
22/25Whether 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.Context economy
14/20Whether the repo fits in a context window, or fights it. Losing marks on file sizes fit in context.Navigability
9/10How quickly anything new can orient itself. Losing marks on repository description.
Higher is better. Accent marks what is costing you most.
Fix these first
01
Agent instruction file
Add an AGENTS.md at the root: what the project is, how to install, how to run, how to test, and the two or three conventions a newcomer always gets wrong.
02
Instruction quality
Instructions earn their keep by naming exact commands. 'Run the tests with `pnpm test`' beats three paragraphs of philosophy.
03
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.
The full marking
Every deduction below names the file or setting it came from.
Instructions 3/27 F
Whether the repo tells an agent how to behave before it starts guessing.
✗Agent instruction file
0/12
None found. Every agent that opens this repo starts from zero.
Add an AGENTS.md at the root: what the project is, how to install, how to run, how to test, and the two or three conventions a newcomer always gets wrong.
Looked for AGENTS.md, CLAUDE.md, .github/copilot-instructions.md, .cursorrules
✗Instruction quality
0/12
Nothing to judge, since there are no instructions.
Instructions earn their keep by naming exact commands. 'Run the tests with `pnpm test`' beats three paragraphs of philosophy.
✓README as an entry point
3/3
README has a clear getting-started section.
Setup 16/20 A-
Whether an agent can install the project and get it running without a human.
✓Deterministic install
6/6
package-lock.json pins the dependency tree.
Found package-lock.json
✓Discoverable commands
6/6
Commands are declared where an agent will look for them.
package.json scripts (dev, dev:ui, dev:cli, dev:electron, build, build:assets…)
✗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 >=22
✓Reproducible environment
2/2
dockerfile gives a known-good environment.
Verification loop 22/25 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
138 test files against 536 source files.
e.g. packages/cli/test/integration/cli-help.test.mjs, packages/core/test/architecture/gateway-service-architecture.test.mjs, packages/core/test/integration/agents/codex-cli-middleware-runtime.test.mjs
✓Test command is discoverable
7/7
An agent can find and run `npm run test`.
✓Continuous integration
4/4
3 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
3/3
Strict type checking is on, which catches a whole class of agent mistakes before they run.
Context economy 14/20 B+
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 22 patterns.
✗File sizes fit in context
0/6
13 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.
packages/electron/bundled-plugins/claude-design/index.cjs — 583KB
packages/core/src/agents/codex/cli-middleware-runtime.ts — 295KB
packages/ui/src/pages/home/components/dashboard.tsx — 250KB
✓Repository weight
5/5
About 49.5MB checked out, which is comfortable.
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 One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control. ## Setup ``` npm ci ``` ## Commands ``` npm run dev # run locally npm run build # produce a build npm run test # run the test suite, must pass before any commit npm run typecheck # type check without emitting npm run dev:ui npm run dev:cli npm run dev:electron npm run build:assets ``` ## Layout - `packages/` 428 source files - `docs/` 81 source files - `build/` 14 source files - `tests/` 5 source files - `extension/` 3 source files - `docker/` 2 source files ## Conventions - Tests live alongside the code they cover, following `packages/cli/test/integration/cli-help.test.mjs`. - TypeScript runs in strict mode. Type errors are the fastest feedback available, so do not weaken it. - CI defines what passing means. See `.github/workflows/docker-release.yml`, and keep it green. - TODO: add the two or three conventions a newcomer always gets wrong here. ## Gotchas - Generated output is committed (`build/`). Search will return the compiled copy, so edit the source, not that. - `packages/electron/bundled-plugins/claude-design/index.cjs` is 583KB. 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/musistudio/claude-code-router.md
Show the mark
The badge re-checks daily, so it keeps up as the repository changes. Use mark again to force it now.
[](https://agentreadme.com/musistudio/claude-code-router)Other TypeScript repositories, marked
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.