skillsight: Command for Claude Code

.claude/commands/pre-pr-quality-check.md

pre-pr-quality-check is a command for Claude Code from PackmindHub/skillsight. It costs 50 tokens per session (414 once invoked), scanned A, original, Apache-2.0.

A pre-pull-request check for a software project that runs dependency installation, linting, type checking, tests, builds, and optionally a Docker build.

In plain words
What is it for?
Use it before opening a pull request, after completing a feature, or when reproducing CI failures locally.
Why use it?
It catches local errors that could otherwise make continuous integration fail or leave type problems unnoticed.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is PackmindHub/skillsight's own configuration. It tells Claude Code how to work on skillsight itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything skillsight configures →

Reuse

Borrowing it

Nothing to install: this file belongs to PackmindHub/skillsight. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/PackmindHub/skillsight/main/.claude/commands/pre-pr-quality-check.md
Clone the repo
git clone --depth 1 https://github.com/PackmindHub/skillsight

Made for: Claude Code.

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 pre-pr-quality-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/packmindhub/skillsight/pre-pr-quality-check.svg)](https://agentmods.dev/commands/packmindhub/skillsight/pre-pr-quality-check)
Your own site
<a href="https://agentmods.dev/commands/packmindhub/skillsight/pre-pr-quality-check"><img src="https://agentmods.dev/badge/commands/packmindhub/skillsight/pre-pr-quality-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 414 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 $0.00050 $0.00414
Opus 5 $0.00025 $0.00207
Sonnet 5 $0.00010 $0.00083
Haiku 4.5 $0.00005 $0.00041

Measured 8d ago against content hash 66c7cc48d31e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pre-pr-quality-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 8d 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.

.claude/commands/pre-pr-quality-check.md · 45 lines

What it actually says

Pre-PR Quality Check

Run every gate locally before opening a pull request so CI passes on the first try. CI (.github/workflows/ci.yml) runs lint, test, build, and a Docker image build — but it does not run typecheck, so type errors can slip past CI entirely. This command runs the CI gates plus typecheck to close that gap.

When to Use

  • Before creating a pull request against main.
  • After finishing a feature, to confirm CI will pass.
  • When CI fails and you want to reproduce it locally.

Checkpoints

  • Are dependencies installed with a frozen lockfile (bun install --frozen-lockfile), matching CI?
  • For the Docker step, is the Docker daemon running locally?

Steps

1. Install dependencies (match CI)

Run bun install --frozen-lockfile so your local tree matches what CI resolves.

2. Lint

Run bun run lint (Biome across backend + frontend). Use bun run check in frontend/ if you also want format checking.

3. Type check (CI gap — do not skip)

Run bun run typecheck. CI does not run this, so it is the most common source of a green CI followed by a broken main.

4. Test

Run bun run test (Bun test runner across all packages).

5. Build

Run bun run build (Vite frontend, then Bun backend build).

6. Optional: production Docker image

If your change touches the Dockerfile or runtime, mirror the CI docker-build job: docker build -t skillsight:ci ..

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. 8d ago First seen · 45 lines · 50 tokens per session scan A 66c7cc48d31e

Subscribe to this mod's changes

pre-pr-quality-check is a command published in the GitHub repository PackmindHub/skillsight (9 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 414 once invoked, about $0.0003 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.