agentreadme

Report · marked 25 Aug 2026

abhigyanpatwari/GitNexus

Solid foundations, held back in a few specific places.

TypeScript · 45,754 stars · 4,988 files · branch main

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
Static type checking
A type checker gives an agent an error message instead of a runtime surprise. It's the second-fastest feedback loop after the compiler.
03
No committed build output
Add these to .gitignore and `git rm -r --cached` them. Generated files pollute search results, so an agent grepping for a function finds the compiled copy and edits the wrong file.

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, .cursorrules
Instruction quality 12/12
Specific enough that an agent can act on it.
14,974 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 18/20 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 (prepare, format, format:check, lint, lint:fix, gitnexus:refresh…)
Environment config 4/4
.env.example documents what the app needs to run.
Pinned runtime version 0/2
No pinned runtime version.
Add a .nvmrc, .python-version, or equivalent so the agent's toolchain matches yours.
Reproducible environment 2/2
.devcontainer/devcontainer.json 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
3475 test files against 4362 source files.
e.g. .devcontainer/translate-plugin-registries.test.cjs, .github/scripts/test_check_tree_sitter_upgrade_readiness.py, .github/scripts/triage/test_embedding_utils.py
Test command is discoverable 7/7
An agent can find and run `pytest`.
Continuous integration 4/4
29 GitHub Actions workflows define what "passing" means.
Lint and format rules 3/3
eslint.config.mjs encodes the house style.
Static type checking 0/3
No static type checking.
A type checker gives an agent an error message instead of a runtime surprise. It's the second-fastest feedback loop after the compiler.
Context economy 10/20 C+

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

No committed build output 3/6
Generated output is committed: .nuxt/.
Add these to .gitignore and `git rm -r --cached` them. Generated files pollute search results, so an agent grepping for a function finds the compiled copy and edits the wrong file.
.gitignore hygiene 3/3
.gitignore covers 72 patterns.
File sizes fit in context 0/6
25 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.
gitnexus/src/mcp/local/local-backend.ts — 373KB
gitnexus/test/unit/group/http-route-extractor.test.ts — 273KB
gitnexus/src/core/run-analyze.ts — 199KB
Repository weight 4/5
About 55.6MB 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 abhigyanpatwari/GitNexus
# AGENTS.md

GitNexus: The Zero-Server Code Intelligence Engine -       GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a git repository (Github, Gitlab, Azure, Local) or ZIP file, and get an interactive knowledge graph with a built in Graph RAG Agent. Perfect for code exploration

## Setup

```
npm ci
```

## Commands

```
npm run lint               # lint
npm run format             # format
npm run prepare
npm run format:check
npm run lint:fix
npm run gitnexus:refresh
npm run gitnexus:full
```

## Layout

- `gitnexus/`                    4121 source files
- `gitnexus-web/`                119 source files
- `eval/`                        52 source files
- `gitnexus-shared/`             38 source files
- `gitnexus-claude-plugin/`      6 source files
- `gitnexus-cursor-integration/` 2 source files

## Conventions

- Tests live alongside the code they cover, following `.devcontainer/translate-plugin-registries.test.cjs`.
- CI defines what passing means. See `.github/workflows/build-tree-sitter-prebuilds.yml`, and keep it green.
- TODO: add the two or three conventions a newcomer always gets wrong here.

## Gotchas

- `gitnexus/src/mcp/local/local-backend.ts` is 373KB. It will not fit comfortably in context, so read it in parts.
- Copy `.env.example` before running anything that needs configuration.

---

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/abhigyanpatwari/GitNexus.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 81 out of 100

[![agent ready](https://agentreadme.com/badge/abhigyanpatwari/GitNexus.svg)](https://agentreadme.com/abhigyanpatwari/GitNexus)

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