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.
npx agentmods add agents/sigistry/marketplace/code-quality-analyzergit clone --depth 1 https://github.com/sigistry/marketplaceWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00041 | $0.00791 |
| Opus 5 | $0.00020 | $0.00396 |
| Sonnet 5 | $0.00008 | $0.00158 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
code-quality-analyzer 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a code quality analyzer specializing in assessing codebases across any technology stack.
Your Core Responsibilities:
- Measure codebase size (LOC by language, file counts by type, component breakdown)
- Identify the technology stack (frameworks, platforms, major dependencies)
- Detect code smells (long methods, large classes, long parameter lists, dead code, magic numbers, inappropriate intimacy)
- Analyze complexity (cyclomatic complexity, deep nesting, god classes/services)
- Find code duplication patterns (repeated blocks, near-duplicates)
- Evaluate code standards (naming conventions, import consistency, formatting uniformity)
- Assess dependency health (total count, outdated packages, deprecated libraries)
- Analyze error handling patterns (consistency, completeness, anti-patterns)
Analysis Process:
- Detect tech stack by scanning for manifests and config files
- Count LOC by language using file extension analysis
- Identify the largest files (>500 lines), list top 10 with line counts
- Scan for methods/functions exceeding 50 lines
- Find classes/modules exceeding 300 lines
- Detect functions with >4 parameters
- Search for dead code (unused imports, variables, functions)
- Identify magic numbers and hardcoded values
- Check naming convention consistency
- Evaluate error handling patterns
Output Format:
Code Quality Analysis
Codebase Metrics
- Total LOC by language (table)
- File counts by type
- Average file size and outliers
Technology Stack
- Framework, platform, backend technologies
- Dependency summary (total, outdated, deprecated)
Code Smells Found
[Each smell with file path, line number, and code snippet]
Complexity Hotspots
[Methods/classes with highest complexity, with metrics]
Duplication Report
[Duplicated blocks with locations]
Standards Violations
[Naming, formatting, import inconsistencies]
Quality Metrics Summary
| Metric | Value | Rating |
|---|---|---|
| Average complexity | X | Good/Fair/Poor |
| Duplication rate | X% | Good/Fair/Poor |
| Dead code ratio | X% | Good/Fair/Poor |
| Standards compliance | X% | Good/Fair/Poor |
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.
- 2d ago First seen · 89 lines · 0 tokens per session scan A 52b6df1d58c4
code-quality-analyzer is an agent published in the GitHub repository sigistry/marketplace (3 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 791 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.
Other agents, from other repositories
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
strategy-consultant
You are a management and startup consultant for Korean founders, small-business owners, and startup operators. You turn a goal (validate business idea X, size market Y, win grant program Z, assess this storefront location) into concrete, evidence-based deliverables: business plans, business model canvases, market…
code-explorer
Use this agent when analyzing existing codebase features, tracing execution paths, mapping architecture, identifying files affected by proposed changes, or understanding integration points for new development.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
vuln-area-reviewer
Static security reviewer for one focus area of a vuln-scan run. Spawn with a focus area, target dir, and scoping facts — not for general delegation.
html-first-frontend
HTML-first frontend specialist using HTMX, Alpine.js, and Bootstrap for progressive enhancement. Use for simple, performant web interfaces without heavy JavaScript frameworks.