# Tech Debt

> Identifies, classifies, and prioritizes technical debt. Use when auditing technical debt, assessing code quality, analyzing maintenance burden, or asking what's slowing us down. Produces categorized inventory with severity rankings, remediation roadmap, and fix recommendations.

- **Type:** Skill
- **Install:** `agentstack add skill-philoserf-claude-code-config-tech-debt`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [philoserf](https://agentstack.voostack.com/s/philoserf)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [philoserf](https://github.com/philoserf)
- **Source:** https://github.com/philoserf/claude-code-config/tree/main/skills/tech-debt

## Install

```sh
agentstack add skill-philoserf-claude-code-config-tech-debt
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Technical Debt Analysis

Systematic methodology for identifying, classifying, and prioritizing technical debt across a codebase. This skill **diagnoses** — it produces an inventory and remediation roadmap but does not modify code.

## When to Use

- User asks about technical debt, maintenance burden, or "what's slowing us down"
- Starting a new engagement with an unfamiliar codebase
- Before a major refactor to scope and prioritize work
- Periodic health check on code quality

## Workflow

### 1. Scan

Walk the codebase and identify debt items using the [debt categories](references/debt-categories.md).

- Glob for project structure and file sizes
- Grep for known smell patterns (TODO/FIXME/HACK, deeply nested code, large files)
- Read representative files in hotspot areas
- Classify each finding into its debt category

**Scaling by codebase size:**

| Files  | Strategy                                                                               |
| ------ | -------------------------------------------------------------------------------------- |
| 
- Scope: 

### Debt Items

| # | Category | Item | Location | Risk | Effort | Tier |
|---|----------|------|----------|------|--------|------|
| 1 | Code     | ...  | ...      | ...  | ...    | ...  |

### Prioritized Roadmap

#### Quick Wins
- [items with rationale]

#### Medium-Term
- [items with rationale]

#### Long-Term
- [items with rationale]

### Recommendations
- [key observations and suggested next steps]
```

## Output Format

1. **Debt Inventory** — Categorized list with locations, risk levels, and effort estimates
2. **Prioritized Roadmap** — Action tiers with rationale for ordering
3. **Recommendations** — Sequencing and scoping advice (what to tackle first and why). Diagnosis and prioritization, not implementation steps.

## Reference Files

Detailed taxonomy and scoring guidance:

- [debt-categories.md](references/debt-categories.md) — Debt types with detection criteria and measurement thresholds
- [roi-framework.md](references/roi-framework.md) — Impact assessment, risk classification, and prioritization tiers

## Do not use when

- Finding specific bugs with file:line precision — use `code-audit`
- Reviewing a specific staged or branch diff — use `diff-review`
- Auditing dependency health specifically — use `deps-audit`
- Performance profiling without structural concerns
- Single-file code review

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [philoserf](https://github.com/philoserf)
- **Source:** [philoserf/claude-code-config](https://github.com/philoserf/claude-code-config)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-philoserf-claude-code-config-tech-debt
- Seller: https://agentstack.voostack.com/s/philoserf
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.