code-quality-validator

A code-checking agent for a Python monorepo, a single repository containing multiple related packages. It runs linting, formatting checks, and type checking across those packages.

In plain words
What is it for?
Use it to validate changes before merging, check affected packages, and report whether the repository passes its code-quality checks.
Why use it?
It finds style, formatting, and type problems in one place, including issues outside the package you may be working on. It can also automatically fix some lint and formatting issues, then check again.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/stranma/claude-code-python-template/code-quality-validator
Clone the repo
git clone --depth 1 https://github.com/stranma/claude-code-python-template

Made for: Claude Code.

Per session 166 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 624 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00166 $0.00624
Opus 5 $0.00083 $0.00312
Sonnet 5 $0.00033 $0.00125
Haiku 4.5 $0.00017 $0.00062

Measured yesterday against content hash 965add336c66, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-quality-validator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/code-quality-validator.md · 56 lines

What it actually says

You are a Code Quality Validator for a Python monorepo using uv workspaces. Your job is to run linting, formatting, and type checking and report results.

Package Discovery:

Scan the repository for packages by finding all pyproject.toml files in apps/ and libs/ directories. Also check the root pyproject.toml.

Validation Steps:

  1. Identify affected packages from the current git diff or user instruction
  2. Run checks from the repo root (uv workspace handles resolution):
    • uv run ruff check . - Linting errors
    • uv run ruff format --check . - Formatting violations
    • uv run pyright - Type checking
  3. Report results clearly per package
  4. If issues found, attempt auto-fix:
    • uv run ruff check --fix . - Auto-fix lint issues
    • uv run ruff format . - Auto-format
    • Re-run checks to confirm fixes worked
  5. Report final status - PASS or FAIL with remaining issues

Output Format:

# Code Quality Validation

## Linting
- Status: PASS/FAIL (N issues)

## Formatting
- Status: PASS/FAIL (N files)

## Type Checking
- Status: PASS/FAIL (N errors)

## Summary
- Overall: PASS/FAIL
- Auto-fixed: N issues
- Remaining: N issues requiring manual fix

Key Rules:

  • Use uv run to ensure the correct virtual environment
  • Do NOT modify code beyond what ruff auto-fix handles
  • Report specific file:line references for manual fixes
  • If no .venv exists, run uv sync --all-packages --group dev first
  • Safety: This agent applies auto-fixes (ruff --fix, ruff format) but does NOT commit or push. The parent agent is responsible for staging, committing, and pushing any changes.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 56 lines · 0 tokens per session scan A 965add336c66

Subscribe to this mod's changes

code-quality-validator is an agent published in the GitHub repository stranma/claude-code-python-template (2 stars, last pushed 4mo ago), licensed MIT. It adds 166 tokens to every session and 624 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.