Report · marked 26 Aug 2026
microsoft/playwright
Ready for an agent to work in without hand-holding.
TypeScript · 95,130 stars · 3,093 files · branch main
88
/100
A
Instructions
24/27Whether the repo tells an agent how to behave before it starts guessing. Losing marks on agent instruction file.Setup
14/14Whether an agent can install the project and get it running without a human. Full marks.Verification loop
25/25Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy. Full marks.Context economy
11/20Whether 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
01
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.
02
Agent instruction file
Rename or symlink to AGENTS.md so tools other than one vendor's can read it. Keeping CLAUDE.md alongside it costs nothing.
03
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 24/27 A
Whether the repo tells an agent how to behave before it starts guessing.
✗Agent instruction file
9/12
CLAUDE.md is present, but not the vendor-neutral AGENTS.md.
Rename or symlink to AGENTS.md so tools other than one vendor's can read it. Keeping CLAUDE.md alongside it costs nothing.
Also found: Copilot instructions
✓Instruction quality
12/12
Specific enough that an agent can act on it.
7,837 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 14/14 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 (ctest, ftest, wtest, wvtest, atest, etest…)
–Environment config
n/a
Not applicable — this reads as a library, with no environment to configure.
✓Pinned runtime version
2/2
The language runtime version is pinned.
package.json engines.node >=20
–Reproducible environment
n/a
Not applicable — a library doesn't need a container to be worked on.
Verification loop 25/25 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
1518 test files against 1602 source files.
e.g. docs/src/images/getting-started/record-new-test.png, docs/src/images/getting-started/run-single-test.png, docs/src/images/getting-started/trace-viewer-failed-test.png
✓Test command is discoverable
7/7
An agent can find and run `npm run test`.
✓Continuous integration
4/4
20 GitHub Actions workflows define what "passing" means.
✓Lint and format rules
3/3
eslint.config.mjs encodes the house style.
✓Static type checking
3/3
Strict type checking is on, which catches a whole class of agent mistakes before they run.
Context economy 11/20 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 43 patterns.
✗File sizes fit in context
0/6
23 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/playwright-client/types/types.d.ts — 1104KB
packages/playwright-core/types/types.d.ts — 1104KB
tests/assets/reading-list/react-dom_18.1.0.js — 1049KB
✗Repository weight
2/5
About 241MB 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 Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API. ## Setup ``` npm ci ``` ## Commands ``` npm run build # produce a build npm run test # run the test suite, must pass before any commit npm run lint # lint npm run ctest npm run ftest npm run wtest npm run wvtest npm run atest ``` ## Layout - `packages/` 782 source files - `tests/` 654 source files - `utils/` 71 source files - `browser_patches/` 52 source files - `examples/` 40 source files ## Conventions - Tests live alongside the code they cover, following `docs/src/images/getting-started/record-new-test.png`. - 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/copilot-setup-steps.yml`, and keep it green. - TODO: add the two or three conventions a newcomer always gets wrong here. ## Gotchas - `packages/playwright-client/types/types.d.ts` is 1104KB. 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/microsoft/playwright.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/microsoft/playwright)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.