Report · marked 25 Aug 2026

deepseek-ai/deepseek-harness

Ready for an agent to work in without hand-holding.

TypeScript · 195,016 stars · 7,903 files · branch master

88 /100 A

Instructions 26/27Whether the repo tells an agent how to behave before it starts guessing. Losing marks on readme as an entry point.Setup 14/14Whether an agent can install the project and get it running without a human. Full marks.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 13/20Whether 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.

Lint and format rules

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

README as an entry point

Give the README an Install and a Usage heading with real commands under each. Agents pattern-match on those headings.

The full marking

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

Instructions 26/27 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.

16,059 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 2/3

README exists but never explains how to get the thing running.

Give the README an Install and a Usage heading with real commands under each. Agents pattern-match on those headings.

Setup 14/14 A+

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 (build, build:official, build:lib, build:lib:host, build:lib:client, build:web…)

scripts/ directory

–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 ^22.19.0 || >=24.0.0

–Reproducible environment n/a

Not applicable — a library doesn't need a container to be worked on.

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

1918 test files against 2819 source files.

e.g. .github/issue-management/policy.test.mjs, apps/cli/tests/args.spec.ts, apps/cli/tests/built-bin.e2e.ts

✓Test command is discoverable 7/7

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

✓Continuous integration 4/4

18 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 13/20 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 41 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.

packages/extensions/tool-cordis/src/api-catalog.ts — 362KB

packages/context/agent-instructions/tests/agent-instructions.spec.ts — 193KB

packages/host/apiproxy/src/api-proxy.ts — 157KB

✗Repository weight 4/5

About 108.9MB 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 — drafted for deepseek-ai/deepseek-harness

undefined

Open the raw markdown or curl -o AGENTS.md agentreadme.com/draft/deepseek-ai/deepseek-harness.md

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/deepseek-ai/deepseek-harness.svg)](https://agentreadme.com/deepseek-ai/deepseek-harness)

Other TypeScript repositories, marked

freeCodeCamp/freeCodeCamp 69 B openclaw/openclaw 68 B nilbuild/developer-roadmap 45 C vuejs/vue 67 B n8n-io/n8n 87 A anomalyco/opencode 80 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