code-debt

code-debt is a skill for Claude Code, Codex from hereinthehive/gotrino-assistant. It costs 53 tokens per session (872 once invoked), scanned A, original, MIT.

A code-review skill that identifies unfinished work and maintenance problems, such as TODO comments, deprecated APIs, unused code, oversized code units, and unexplained constants.

In plain words
What is it for?
It helps review a file, module, or directory, assess the impact of code-level debt, and plan cleanup work.
Why use it?
It makes deferred work and code that may increase future maintenance effort easier to find before cleanup or a release.

Skill for Claude CodeCodex

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

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.

agentmods
npx agentmods add skills/hereinthehive/gotrino-assistant/code-debt
Any agent
npx skills add hereinthehive/gotrino-assistant --skill code-debt
Clone the repo
git clone --depth 1 https://github.com/hereinthehive/gotrino-assistant

Made for: Claude Code, Codex.

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 code-debt

README.md
[![agentmods](https://agentmods.dev/badge/skills/hereinthehive/gotrino-assistant/code-debt.svg)](https://agentmods.dev/skills/hereinthehive/gotrino-assistant/code-debt)
Your own site
<a href="https://agentmods.dev/skills/hereinthehive/gotrino-assistant/code-debt"><img src="https://agentmods.dev/badge/skills/hereinthehive/gotrino-assistant/code-debt.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 872 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00053 $0.00872
Opus 5 $0.00026 $0.00436
Sonnet 5 $0.00011 $0.00174
Haiku 4.5 $0.00005 $0.00087

Measured 5d ago against content hash 8b57df948d6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 5d 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/code-debt/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Debt

Surface code-level debt and understand what it's costing the project.

Philosophy

"What does our code still owe us that we haven't paid?"

Every TODO is a promise. Every deprecated call is a migration the team chose to defer. Every commented-out block is a decision someone hasn't made. Code-debt names those debts so the team can decide which to pay.

Not a linter. A linter asks "does this match a rule?" This skill asks "what have we left unfinished, and what's it costing us?"

Scope

The user may specify a file path, glob pattern, or directory. If not specified, ask: "Which path or module would you like to analyze?"

Config Integration

Follow the migration preflight in references/config-migration.md.

After preflight, read .assistant-config.md for:

  • Debt Scope overrides (code-debt.max-function-lines, etc.)
  • Acknowledged Debt entries for this dimension (skip these)
  • Architecture Principles (optional context for judgment)

If no config exists, use heuristic defaults from references/code-debt-patterns.md.

Stack Detection

Glob for manifest files to infer language conventions:

  • package.json → JavaScript/TypeScript
  • pyproject.toml / requirements.txt → Python
  • Gemfile → Ruby
  • go.mod → Go
  • Cargo.toml → Rust

Show detected stack in the output header. If unclear, proceed with language-agnostic patterns only.

Process

1. Understand context

Read a representative file or two from the scope to understand the codebase's style. Note whether the project already tracks debt in comments (e.g. TODO(#1234) with issue refs) — those are tracked items, not untracked debt.

2. Scan

Use Grep for each pattern category. See references/code-debt-patterns.md for the full list. Collect raw findings with file:line locations.

For rename/identifier drift, scan the whole project tree — not just source. Config files, .gitignore, agent definitions, CI configs, and docs commonly hold the old name after a source-only rename. The point of this check is the blast radius.

Read the full file on GitHub · 89 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. 5d ago First seen · 89 lines · 53 tokens per session scan A 8b57df948d6b

Subscribe to this mod's changes

code-debt is a skill published in the GitHub repository hereinthehive/gotrino-assistant (5 stars, last pushed 4mo ago), licensed MIT. It adds 53 tokens to every session and 872 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens