tech-debt-assessment

tech-debt-assessment is a skill for Claude Code from sethdford/claude-skills. It costs 38 tokens per session (667 once invoked), scanned A, original, MIT.

A method for finding and ranking technical debt: code or design choices that make future changes, maintenance, or bug fixes harder. It weighs each problem’s likely impact against the effort needed to fix it.

In plain words
What is it for?
Reviewing system health, identifying issues such as tangled dependencies or outdated libraries, estimating their effect on delivery and risk, and creating a refactoring or replacement roadmap.
Why use it?
Teams often know that a codebase is slowing them down but cannot agree which problems matter most. This provides a way to catalogue, estimate, prioritise, and plan the reduction of that maintenance burden.

Skill for Claude Code

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

Part of the architecture-governance plugin — 7 skills shipped together

Good fit Reviewing system health, identifying issues such as tangled dependencies or outdated libraries, estimating their effect on delivery and risk, and creating a refactoring or replacement roadmap.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sethdford/claude-skills/tech-debt-assessment
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 sethdford/claude-skills --skill tech-debt-assessment
Clone the repo
git clone --depth 1 https://github.com/sethdford/claude-skills

Made for: Claude Code.

Or install architecture-governance, the plugin that ships this one along with the rest of its 7 skills.

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 tech-debt-assessment

README.md
[![agentmods](https://agentmods.dev/badge/skills/sethdford/claude-skills/tech-debt-assessment/github.svg)](https://agentmods.dev/skills/sethdford/claude-skills/tech-debt-assessment)
Your own site
<a href="https://agentmods.dev/skills/sethdford/claude-skills/tech-debt-assessment"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/tech-debt-assessment/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 tech-debt-assessment

Your own site · 80×15
<a href="https://agentmods.dev/skills/sethdford/claude-skills/tech-debt-assessment"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/tech-debt-assessment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 667 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 $0.00038 $0.00667
Opus 5 $0.00019 $0.00333
Sonnet 5 $0.00008 $0.00133
Haiku 4.5 $0.00004 $0.00067

Measured 11d ago against content hash 668e0008a70c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

tech-debt-assessment 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 11d 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.

architect/architecture-governance/skills/tech-debt-assessment/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tech Debt Assessment

Systematically measure technical debt, prioritize paydown, and track progress.

Context

You are assessing technical debt in the system. Quantify impact (velocity reduction, risk increase), estimate effort to fix, prioritize based on ROI. Read code, metrics, team feedback.

Domain Context

Based on technical debt frameworks (Steve McConnell, Martin Fowler):

  • Types of Debt: Deliberate (knowingly cut corners for speed), accidental (poor design decisions), negligent (avoidable bad practices)
  • Impact: Slows feature delivery (velocity decrease), increases bugs (quality risk), complicates future changes
  • Interest Payments: Cost to maintain bad code; time spent working around it; bugs from complexity
  • Paydown: Refactoring, rewriting, deprecating; costs time/resources upfront but reduces future interest

Instructions

  1. Catalog Debt Items: Interview team: "What slows us down?" Common themes: hard-to-test code, tangled dependencies, missing documentation, outdated libraries.

  2. Quantify Impact: For each debt item, how much does it slow velocity? Example: "Test coverage < 30% makes refactoring 3x slower". Measure days/quarter lost to debt.

  3. Estimate Paydown Effort: How long to fix? Refactor module: 2 weeks. Rewrite component: 1 month. Replace library: 3 days. Be realistic; add 50% buffer.

  4. Calculate ROI: Paydown cost vs interest savings. Refactor for 2 weeks (80 hours) to save 5 hours/quarter in reduced bugs and faster changes. Payoff: ~16 quarters (4 years).

  5. Prioritize: High impact + low effort = do first. High impact + high effort = plan for next quarter. Low impact = defer or accept. Build paydown roadmap: 20% of sprint capacity for debt.

Anti-Patterns

  • Debt Without Metrics: "Our code is messy" without quantifying impact. Result: hard to justify paydown. Guard: Quantify slowness; track velocity impact.
  • Paydown Without Benefit: Refactor for refactoring's sake. Result: effort spent, velocity unchanged. Guard: Only pay down debt with measurable benefit (fewer bugs, faster changes).
  • Ignoring Debt Accumulation: Always add features, never refactor. Result: exponential slowdown. Guard: Allocate 20% of capacity for debt; enforce discipline.
  • Wrong Prioritization: Pay down low-impact debt first. Result: effort wasted, high-impact debt still blocking. Guard: Prioritize by impact × frequency, not just preference.

Read the full file on GitHub · 47 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. 11d ago First seen · 47 lines · 38 tokens per session scan A 668e0008a70c

Subscribe to this mod's changes

tech-debt-assessment is a skill published in the GitHub repository sethdford/claude-skills (40 stars, last pushed 6mo ago), licensed MIT. It adds 38 tokens to every session and 667 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 2026-08-30.