design-debt

design-debt is a skill for Claude Code from hereinthehive/gotrino-assistant. It costs 45 tokens per session (674 once invoked), scanned A, original, MIT.

A codebase review that finds design drift, such as inconsistent error handling, naming, response formats, architecture, or duplicated business logic.

In plain words
What is it for?
It helps inspect a bounded module or layer, compare its patterns with declared principles or inferred conventions, and identify inconsistencies.
Why use it?
It reveals why a system is becoming harder to understand even when tests and lint checks still pass.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the gotrino-assistant plugin — 18 skills, 1 agent shipped together

Good fit It helps inspect a bounded module or layer, compare its patterns with declared principles or inferred conventions, and identify inconsistencies.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hereinthehive/gotrino-assistant/design-debt
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 hereinthehive/gotrino-assistant --skill design-debt
Clone the repo
git clone --depth 1 https://github.com/hereinthehive/gotrino-assistant

Made for: Claude Code.

Or install gotrino-assistant, the plugin that ships this one along with the rest of its 18 skills, 1 agent.

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 design-debt

README.md
[![agentmods](https://agentmods.dev/badge/skills/hereinthehive/gotrino-assistant/design-debt/github.svg)](https://agentmods.dev/skills/hereinthehive/gotrino-assistant/design-debt)
Your own site
<a href="https://agentmods.dev/skills/hereinthehive/gotrino-assistant/design-debt"><img src="https://agentmods.dev/badge/skills/hereinthehive/gotrino-assistant/design-debt/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 design-debt

Your own site · 80×15
<a href="https://agentmods.dev/skills/hereinthehive/gotrino-assistant/design-debt"><img src="https://agentmods.dev/badge/skills/hereinthehive/gotrino-assistant/design-debt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 674 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 $0.00045 $0.00674
Opus 5 $0.00023 $0.00337
Sonnet 5 $0.00009 $0.00135
Haiku 4.5 $0.00005 $0.00067

Measured 12d ago against content hash 21dcb116bb7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

design-debt 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 12d 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.

skills/design-debt/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Debt

Surface drift — the gap between how the codebase was meant to be structured and how it actually is.

Philosophy

"Is our system getting harder to reason about because of drift?"

Design debt is quiet. No test fails, no lint warns. But new contributors ask more questions, changes take longer, bugs appear in "how do these modules talk to each other." Design-debt finds the drift before it compounds.

Not a refactoring plan. The value is spotting inconsistency, not prescribing a fix. The team decides whether to realign or to formalize the new pattern.

Scope

User may specify a directory. Default: ask which part of the codebase to focus on. This skill works best on a bounded slice (a module, a layer), not whole-codebase scans.

Config Integration

Follow references/config-migration.md for preflight.

Read .assistant-config.md for:

  • Architecture Principles (optional — ground truth if declared)
  • Stack
  • Acknowledged Debt

If no architecture principles are declared, infer the dominant pattern from the code and flag deviations.

Stack Detection

Language/framework context matters (Express vs. Next.js handlers have different norms). Detect via manifest as in other dimensions.

Process

1. Understand context

Read a representative handful of files in the scope. Identify:

  • The dominant structural pattern (e.g. "handlers are thin, delegate to services")
  • The dominant error-handling style (e.g. "try/catch, JSON envelope")
  • The dominant naming convention

2. Scan

  • Error handling inconsistency: read all handlers (or equivalent). Compare error shapes.
  • Response shape inconsistency: same, for success responses.
  • Naming inconsistency: Glob filenames, Grep function names.
  • Architectural drift: Grep for imports that cross declared boundaries (e.g. services importing handlers, handlers doing direct DB calls).
  • Duplicated logic: Grep for similar function signatures across files.

3. Group by concern

Read the full file on GitHub · 79 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. 12d ago First seen · 79 lines · 45 tokens per session scan A 21dcb116bb7a

Subscribe to this mod's changes

design-debt is a skill published in the GitHub repository hereinthehive/gotrino-assistant (5 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 674 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.