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 skills add ArabelaTso/Skills-4-SE --skill technical-debt-analyzergit clone --depth 1 https://github.com/ArabelaTso/Skills-4-SEWrote 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.
[](https://agentmods.dev/skills/arabelatso/skills-4-se/technical-debt-analyzer)<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/technical-debt-analyzer"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/technical-debt-analyzer/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.
<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/technical-debt-analyzer"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/technical-debt-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00083 | $0.06442 |
| Opus 5.5 | $0.00033 | $0.02577 |
| Sonnet 5.5 | $0.00017 | $0.01288 |
| Haiku 4.5 | $0.00008 | $0.00644 |
Grade A, and why
technical-debt-analyzer scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const response = await axios.get('https://api.example.com'); How it starts
The opening of the file, as written. The whole thing — 1,048 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Debt Analyzer
Systematically identify, categorize, and prioritize technical debt across codebases. Provides actionable insights into code quality, architectural issues, and maintenance risks.
Core Capabilities
1. Code Quality Analysis
Identify code-level technical debt:
- Code smells - Long methods, large classes, duplicated code
- Complexity metrics - Cyclomatic complexity, nesting depth
- Naming issues - Poor variable/function names, inconsistent conventions
- Dead code - Unused functions, unreachable code, commented code
- Magic numbers - Hard-coded values without explanation
- Anti-patterns - Common design mistakes and bad practices
2. Architectural Debt
Detect structural and design issues:
- Tight coupling - Excessive dependencies between modules
- Missing abstractions - Duplicated logic that should be extracted
- Layer violations - Breaking architectural boundaries
- God objects - Classes/modules with too many responsibilities
- Circular dependencies - Modules depending on each other
- Inconsistent patterns - Mixed architectural styles
3. Maintenance Risk Assessment
Identify high-maintenance areas:
- Change frequency - Files modified frequently (hotspots)
- Bug density - Areas with recurring bugs
- Test coverage gaps - Critical code without tests
- Complexity + change - Complex code that changes often (highest risk)
- Knowledge concentration - Code only one person understands
- Outdated dependencies - Old libraries with security issues
4. Documentation Debt
Find documentation gaps:
- Missing documentation - Undocumented public APIs
- Outdated comments - Comments contradicting code
- Poor commit messages - Unclear change history
- Incomplete README - Setup/usage not documented
- Missing architecture docs - No design documentation
5. Test Debt
Assess test quality issues:
- Low coverage - Critical paths untested
- Flaky tests - Tests that fail intermittently
- Slow tests - Tests that slow down CI/CD
- Test duplication - Redundant test logic
- Missing test types - No integration/E2E tests
- Brittle tests - Tests that break with minor 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.
- 2mo ago First seen · 1,048 lines · 83 tokens per session scan A af3b8b54f5bc
technical-debt-analyzer is a skill published in the GitHub repository ArabelaTso/Skills-4-SE (260 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 83 tokens to every session and 6,442 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
technical-debt-analyzer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| technical-debt-analyzerArabelaTso/Skills-4-SE | Skill | 260 | 2mo ago | Apache-2.0 | A | 83 | Claude Code, Codex |
| skill-pr-reviewsaitarrun/Sdlc-ai-workflow | Skill | 7 | 1mo ago | none | A | 65 | Claude Code |
| improve-codebase-architecturesaitarrun/Sdlc-ai-workflow | Skill | 7 | 1mo ago | none | A | 68 | Claude Code |
| skill-code-reviewsaitarrun/Sdlc-ai-workflow | Skill | 7 | 1mo ago | none | A | 19 | Claude Code |
| skill-code-standardssaitarrun/Sdlc-ai-workflow | Skill | 7 | 1mo ago | none | A | 23 | Claude Code |
| skill-code-qualitysaitarrun/Sdlc-ai-workflow | Skill | 7 | 1mo ago | none | A | 34 | Claude Code |
| teachsaitarrun/Sdlc-ai-workflow | Skill | 7 | 1mo ago | none | A | 15 | Claude Code |