dev-quality-report

dev-quality-report is a skill for Claude Code from cicababba/claude-plugins-marketplace. It costs 45 tokens per session (1,389 once invoked), scanned A, original, MIT.

A skill that creates a saved report about code quality, including the paths it analyzed and its findings. The report is stored in the project's development-session reports folder.

In plain words
What is it for?
Use it to analyze the whole repository or selected paths during a quality check or session wrap-up. It reports issues found by a code-quality analyzer and records whether the analysis finished or was stopped.
Why use it?
It keeps quality checks available after the current session instead of leaving the findings only in conversation. It also ignores common generated and dependency folders by default.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the dev-workflow-automation plugin — 9 skills, 4 commands, 11 agents shipped together

Good fit Use it to analyze the whole repository or selected paths during a quality check or session wrap-up. It reports issues found by a code-quality analyzer and records whether the analysis finished or was stopped.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cicababba/claude-plugins-marketplace/dev-quality-report
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 cicababba/claude-plugins-marketplace --skill dev-quality-report
Clone the repo
git clone --depth 1 https://github.com/cicababba/claude-plugins-marketplace

Made for: Claude Code.

Or install dev-workflow-automation, the plugin that ships this one along with the rest of its 9 skills, 4 commands, 11 agents.

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 dev-quality-report

README.md
[![agentmods](https://agentmods.dev/badge/skills/cicababba/claude-plugins-marketplace/dev-quality-report/github.svg)](https://agentmods.dev/skills/cicababba/claude-plugins-marketplace/dev-quality-report)
Your own site
<a href="https://agentmods.dev/skills/cicababba/claude-plugins-marketplace/dev-quality-report"><img src="https://agentmods.dev/badge/skills/cicababba/claude-plugins-marketplace/dev-quality-report/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 dev-quality-report

Your own site · 80×15
<a href="https://agentmods.dev/skills/cicababba/claude-plugins-marketplace/dev-quality-report"><img src="https://agentmods.dev/badge/skills/cicababba/claude-plugins-marketplace/dev-quality-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,389 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 $0.00045 $0.01389
Opus 5 $0.00023 $0.00694
Sonnet 5 $0.00009 $0.00278
Haiku 4.5 $0.00005 $0.00139

Measured 10d ago against content hash 896fd672eacb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

dev-quality-report 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 10d 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.

dev-workflow-automation/skills/dev-quality-report/SKILL.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev Quality Report

This skill generates persistent code quality reports.

When to Use

  • During /quality-check command
  • When quality check is requested during /end
  • When analyzing code quality for specific paths
  • Independent of any active session

Input

  • paths: List of paths to analyze (default: repo root)
  • options:
    • include: Glob patterns to include
    • exclude: Glob patterns to exclude
    • defaultExcludes: boolean (default: true) - Apply default ignore rules

Responsibilities

  • Ask user which paths to analyze (if not provided)
  • Apply default ignore rules (unless disabled)
  • Generate unique reportId (8-char hex)
  • Generate report path: .claude/dev-sessions/quality-reports/YYYYMMDD-HHmm-qa-{reportId}.md
  • Write initial report with Status: PENDING
  • Call code-quality-analyzer agent in read-only mode
  • Rewrite report with full analysis and Status: DONE or ABORTED
  • Return report path and summary

Default Ignore Rules

Always ignored unless defaultExcludes: false:

  • **/node_modules/**
  • **/.git/**
  • **/dist/**, **/build/**, **/.next/**, **/.vite/**
  • **/coverage/**, **/.turbo/**, **/.cache/**
  • **/tmp/**, **/.tmp/**
  • **/package-lock.json, **/pnpm-lock.yaml, **/yarn.lock
  • **/*.min.*

MUST

  • Use artifact-fs-manager for all file operations
  • Never modify repository source files
  • Never change any session Status
  • Always set report Status to PENDING before analysis
  • Always set report Status to DONE or ABORTED after

MUST NOT

  • Modify any source code files
  • Install or change dependencies
  • Change session status
  • Run commands that modify the codebase

Process

Step 1: Determine Paths

If paths not provided:

  1. Ask user: "Which paths should I analyze? (default: repo root)"
  2. Accept user input or use default

Step 2: Apply Ignore Rules

  1. Start with default ignore patterns (if defaultExcludes: true)
  2. Add any additional exclude patterns
  3. Apply include patterns to narrow scope

Read the full file on GitHub · 233 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. 10d ago First seen · 233 lines · 45 tokens per session scan A 896fd672eacb

Subscribe to this mod's changes

dev-quality-report is a skill published in the GitHub repository cicababba/claude-plugins-marketplace (3 stars, last pushed 9mo ago), licensed MIT. It adds 45 tokens to every session and 1,389 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 2026-08-31.