qa-check

qa-check is a skill for Claude Code, Codex from DavidVujic/my-eca-config. It costs 37 tokens per session (1,693 once invoked), scanned A, original, MIT.

A repository quality-check assistant that discovers and runs the project's linting and unit-test commands. Linting checks code for style and common errors; unit tests check small pieces of behavior.

In plain words
What is it for?
It examines files such as Justfile, Makefile, pyproject.toml, and package.json, identifies Python or JavaScript/TypeScript projects, sets up an available virtual environment, and runs the appropriate checks.
Why use it?
It removes the need to remember project-specific quality commands and provides a consistent check after code changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It examines files such as Justfile, Makefile, pyproject.toml, and package.json, identifies Python or JavaScript/TypeScript projects, sets up an available virtual environment, and runs the appropriate checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/davidvujic/my-eca-config/qa-check
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.

Any agent
npx skills add DavidVujic/my-eca-config --skill qa-check
Clone the repo
git clone --depth 1 https://github.com/DavidVujic/my-eca-config

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for qa-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidvujic/my-eca-config/qa-check/github.svg)](https://agentmods.dev/skills/davidvujic/my-eca-config/qa-check)
Your own site
<a href="https://agentmods.dev/skills/davidvujic/my-eca-config/qa-check"><img src="https://agentmods.dev/badge/skills/davidvujic/my-eca-config/qa-check/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for qa-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/davidvujic/my-eca-config/qa-check"><img src="https://agentmods.dev/badge/skills/davidvujic/my-eca-config/qa-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,693 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00037 $0.01693
Opus 5 $0.00018 $0.00847
Sonnet 5 $0.00007 $0.00339
Haiku 4.5 $0.00004 $0.00169

Measured 9d ago against content hash def83230997c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

qa-check 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 9d ago.

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.

skills/qa-check/SKILL.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Check Skill

Purpose

Verify code quality after changes by running linting and unit tests. This skill discovers the correct commands for the current repository automatically, so it works across different project setups and languages.

This skill MUST be used after an agent produces or modifies code.


Procedure

Follow these steps strictly and in order.

Step 1 — Locate the repository root

Run:

git rev-parse --show-toplevel

Capture the output as REPO_ROOT. All subsequent file lookups and commands use REPO_ROOT as the working directory.


Step 2 — Identify the project type

Check for project manifest files in REPO_ROOT:

  • If pyproject.toml, setup.py, or setup.cfg exists → project type is Python.

  • Else if package.json exists → project type is JS/TS.

  • Else → unknown. Report:

    "Unable to determine project type. Skipping QA checks."

    and stop — do not continue to subsequent steps.


Step 3 — Set up the environment

Python projects

Check for a virtual environment in this order:

  1. REPO_ROOT/.venv/bin/activate
  2. REPO_ROOT/venv/bin/activate

If found, prefix every shell command in subsequent steps with:

source REPO_ROOT/.venv/bin/activate &&

(using the path that was found).

This ensures that just, make, and direct tool invocations all run inside the activated virtual environment.

If no virtual environment is found, run commands without a prefix.

JS/TS projects

No environment activation is needed. Commands will use the package manager detected from the project:

  • If REPO_ROOT/pnpm-lock.yaml exists → use pnpm.
  • Else if REPO_ROOT/yarn.lock exists → use yarn.
  • Else → use npm.

Capture the chosen package manager as PM for use in later steps.


Step 4 — Discover the lint command

Try each source below in order. Stop at the first match.

4a — Justfile

Check if REPO_ROOT/justfile or REPO_ROOT/Justfile exists. If it does, look for a recipe named lint (a line starting with lint followed by : or arguments).

Read the full file on GitHub · 240 lines

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. 9d ago First seen · 240 lines · 37 tokens per session scan A def83230997c

Subscribe to this mod's changes

qa-check is a skill published in the GitHub repository DavidVujic/my-eca-config (11 stars, last pushed 12d ago), licensed MIT. It adds 37 tokens to every session and 1,693 once invoked, about $0.0002 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 2026-08-30.