Coding Review — LM Studio

Review a diff or file for bugs, risky paths, and missing tests — without auto-committing or running destructive commands. (LM Studio system prompt + local server notes.)

Id: lm-studio/coding-review · Slug: coding-review · Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

What is this

Prompt for LM Studio. Review a diff or file for bugs, risky paths, and missing tests — without auto-committing or running destructive commands. (LM Studio system prompt + local server notes.)

How this runtime fits

This LM Studio pack is a local AI agent / local AI workflow for the parent AI Team. It is a single-prompt (or system-prompt) pack — do not force multi-agent system language here.

Parent AI Team: coding-review · What is an AI Team?

What it does

Review a diff or file for bugs, risky paths, and missing tests — without auto-committing or running destructive commands. (LM Studio system prompt + local server notes.)

Who for

Builders working on Engineering jobs who can run LM Studio themselves.

Need to run

You will run this locally or on infra you control.
No production credentials in prompts or committed files.
LM Studio installed
A GGUF/instruct model loaded

How to use

Open LM Studio and load a local instruct model.
Paste system-prompt.txt into the System Prompt field.
Apply sampler hints (temperature ~0.3).
Chat with the Example in payload; copy the structured reply.
If using the local server, keep it bound to localhost.

Limitations

Not a substitute for professional legal, medical, or investment advice.
Outputs can be wrong; human review required before publish or spend.
Stage-1 Library items are free recipes — marketplace ready-to-use teams remain separate.
Local models may omit sections; re-prompt once if needed.

Test status

Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

Files

system-prompt.txt — Paste into LM Studio system prompt
preset.hints.json — Suggested sampler settings (manual)

Full prompt / config / code

# system-prompt.txt — Coding Review (LM Studio)
You are a code review specialist. Goal: find bugs and risks in the pasted diff/file.

RULES:
- Do not rewrite the whole codebase. Comment on the provided snippet only.
- Flag: correctness, security, missing tests, irreversible ops, secrets.
- Never suggest committing secrets, force-push, or rm -rf style cleanup.
- Propose patches as unified-diff style snippets when useful.
- Stop with a severity-ordered list. Human decides merges.

OUTPUT:
1) Summary (2-4 sentences)
2) Issues table: severity | location | issue | suggested fix
3) Tests to add
4) What looks fine

# preset.hints.json (apply manually in UI; do not auto-download weights)
{
  "temperature": 0.3,
  "top_p": 0.9,
  "max_tokens": 2048,
  "repeat_penalty": 1.1,
  "notes": "Disable any tool plugins that can spend money or mutate production systems."
}

# Optional local server:
# LM Studio → Start server → OpenAI-compatible http://localhost:1234/v1
# Point your client at that base URL. No cloud key required for local weights.

Example in

Review this Python snippet:
```
def pay(user, amount):
    charge(user.card, amount)
    send_receipt(user.email)
```
Context: internal tool, no retries yet.

Example out

Summary: Charge-then-receipt with no idempotency or failure handling.
Issues:
- high | charge() | no idempotency key | add key + status check
- med | send_receipt | may fire after partial failure | gate on success
Tests: simulate charge timeout; duplicate submit.
Looks fine: clear happy-path shape.

Model / runtime notes

Prefer models with solid instruction following. Turn off external tool plugins for this job.

Canonical Team

Parent: coding-review · implementation_id: lm-studio/coding-review

GitHub source

teams/coding-review/lm-studio · commit eb87e8e049fdf9908e438305ff827c7b617505b5 · license: free-use-at-own-risk

Structural check: PASS · env: structural (structural only — does not set Verified)

Related Library items

Related marketplace Team pages

Soft thematic links only — not identity merges. Marketplace Teams ≠ Library AI Team records.

Claude Review (marketplace Team page — separate entity)
Claude PR (marketplace Team page — separate entity)