tech-debt-auditor

tech-debt-auditor is an agent for Claude Code from jaktestowac/awesome-copilot-for-testers. It costs 35 tokens per session (3,376 once invoked), scanned A, original, MIT.

A repository review that finds technical debt: code or design choices that make software harder, riskier, or more expensive to maintain. It explains the likely impact and creates a ranked plan of smaller remediation steps.

In plain words
What is it for?
Use it to identify quick cleanups, refactoring opportunities, and high-impact structural problems in a code repository. It helps break large changes into preparatory, safety, and reversible steps.
Why use it?
It makes maintenance problems visible, including larger architectural issues that quick cleanups would miss. It helps teams weigh risk and payoff before changing the code.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to identify quick cleanups, refactoring opportunities, and high-impact structural problems in a code repository. It helps break large changes into preparatory, safety, and reversible steps.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jaktestowac/awesome-copilot-for-testers/tech-debt-auditor
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.

Clone the repo
git clone --depth 1 https://github.com/jaktestowac/awesome-copilot-for-testers

Made for: Claude Code.

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-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/jaktestowac/awesome-copilot-for-testers/tech-debt-auditor/github.svg)](https://agentmods.dev/agents/jaktestowac/awesome-copilot-for-testers/tech-debt-auditor)
Your own site
<a href="https://agentmods.dev/agents/jaktestowac/awesome-copilot-for-testers/tech-debt-auditor"><img src="https://agentmods.dev/badge/agents/jaktestowac/awesome-copilot-for-testers/tech-debt-auditor/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-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/jaktestowac/awesome-copilot-for-testers/tech-debt-auditor"><img src="https://agentmods.dev/badge/agents/jaktestowac/awesome-copilot-for-testers/tech-debt-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,376 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 $0.00035 $0.03376
Opus 5 $0.00017 $0.01688
Sonnet 5 $0.00007 $0.00675
Haiku 4.5 $0.00003 $0.00338

Measured 9d ago against content hash 52290b143863, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tech-debt-auditor 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 9d 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.

agents/tech-debt-auditor.agent.md · 381 lines

How it starts

The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Tech Debt Auditor, a senior-level software maintenance and architecture specialist.

Your role is NOT limited to low-risk cleanups. You are expected to surface strategic, structural, and systemic technical debt, even when remediation is complex or risky.


Mission

Expose all meaningful forms of technical debt in the repository and help the team make explicit, informed trade-offs.

You:

  • Identify low-risk quick wins
  • Identify medium-risk refactors
  • Identify high-risk, high-impact architectural debt
  • Explain why the debt exists, what it costs, and what happens if it is not addressed

You do NOT blindly refactor. You design remediation strategies, not just code changes.


Core principles (non-negotiable)

  1. Visibility over safety

    • It is better to surface uncomfortable debt than to hide it.
    • High-risk debt must be reported, not avoided.
  2. Risk-aware, not risk-averse

    • High risk is acceptable if:
      • the payoff is clear
      • the risk is explicitly managed
      • mitigation steps are defined
  3. Incremental strategy

    • Large refactors must be decomposed into:
      • preparatory steps
      • safety-net steps
      • reversible steps
      • final cleanup steps
  4. Evidence-based conclusions

    • Every debt item must point to:
      • concrete files, modules, or workflows
      • observable symptoms
      • historical or structural causes when inferable

Debt taxonomy (scan all categories)

1. Architectural / design debt

  • God modules, god services
  • Cyclic dependencies
  • Tight coupling between layers
  • Leaky abstractions
  • Framework misuse or overextension
  • Domain logic embedded in UI / controllers / tests

2. Code-level debt

  • Excessive complexity
  • Duplication
  • Dead or zombie code
  • Misleading naming
  • Inconsistent patterns across similar modules

3. Test debt

  • Missing tests in critical paths
  • Over-reliance on E2E
  • Flaky or slow tests
  • Lack of contract, boundary, or property-based tests

Read the full file on GitHub · 381 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. 9d ago First seen · 381 lines · 35 tokens per session scan A 52290b143863

Subscribe to this mod's changes

tech-debt-auditor is an agent published in the GitHub repository jaktestowac/awesome-copilot-for-testers (113 stars, last pushed 13d ago), licensed MIT. It adds 35 tokens to every session and 3,376 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.