Skip to content
Agentmart
Submit a tool

arch-lint-llm

Review TypeScript architecture for semantic ownership violations that static lint cannot detect.

Skill by motxx

IndexedMIT
Write a review

Chalk Labs

Need help deploying arch-lint-llm?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/motxx-arch-lint-llm

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Review TypeScript architecture for semantic ownership violations that static lint cannot detect. Use for architecture reviews and substantial structural changes under packages/.

Use cases: ml

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/arch-lint-llm

What's inside

Skill name
arch-lint-llm
Description
Review TypeScript architecture for semantic ownership violations that static lint cannot detect. Use for architecture reviews and substantial structural changes under packages/.
License
MIT
Instructions
30 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

Review architecture without modifying files.

Run `deno task lint:arch --errors-only` first. Stop if it fails; static lint owns structural violations.

Read each relevant non-test file in full, plus the modules that share or should own its responsibility. If the user gives no scope, review changed `packages/*/src/**/*.ts(x)` files from `origin/main...HEAD` that have at least 150 lines.

Apply the single-purpose rule from `AGENTS.md`: every function, module, package, adapter, and public surface has one owner responsibility.

Report only findings supported by concrete code:

- **L001 Cohesion:** one module owns unrelated responsibilities.
- **L002 Service locator:** mutable ambient state hides I/O, configuration, or dependency injection.
- **L003 Duplication:** two owners implement the same decision, invariant, or state machine.
- **L004 Intimacy:** a module depends on another module's internals instead of its public API.
- **L005 Function responsibility:** one function contains independently replaceable responsibilities rather than orchestrating named parts.
- **L006 Domain leakage:** domain logic reads time, randomness, configuration, or I/O without an injected port.
- **L007 Boundary ownership:** a boundary becomes a second owner or bundles concerns that should remain independently replaceable.

Do not report file length, style, re-export-only barrels, tests, or rules already owned by static lint. When intent is unclear, do not guess.

For each finding, give severity, path and line, category, evidence, consequence, and the smallest ownership correction. Use HIGH for a concrete second owner, divergence risk, or blocked isolation; MEDIUM only when the structure is suspicious but may be intentional.

After a clean review, or after the user explicitly accepts every finding, record the exact reviewed diff:

```bash
deno run --allow-read --allow-run --allow-write --allow-env \
  scripts/arch-lint-llm-verify.ts --record
```

From motxx/anchr, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 30, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from motxx

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get arch-lint-llm running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying arch-lint-llm?

CallGet help
Cite this page

arch-lint-llm skill. Agent Mart. https://agentmart.dev/skills/motxx-arch-lint-llm (last updated 2026-10-24)