tech-debt-tracking

tech-debt-tracking is a skill for Claude Code from Vimalk0703/shipworthy. It costs 24 tokens per session (491 once invoked), scanned A, original, MIT.

A record-keeping workflow for technical debt, meaning shortcuts or known problems that may cost more to fix later. It stores each item with its reason, severity, expected effort, impact, and affected files.

In plain words
What is it for?
Use it whenever you choose a quick workaround, skip a test, hardcode a value, bypass a quality check, or leave a TODO, and review the outstanding items at session start.
Why use it?
It prevents temporary workarounds, skipped tests, deprecated APIs, and TODOs from disappearing from view. Developers can see which shortcuts need attention and why they were taken.

Skill for Claude Code

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

Part of the shipworthy plugin — 66 skills, 7 commands, 6 agents, 3 hooks 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/vimalk0703/shipworthy/tech-debt-tracking
Any agent
npx skills add Vimalk0703/shipworthy --skill tech-debt-tracking
Clone the repo
git clone --depth 1 https://github.com/Vimalk0703/shipworthy

Made for: Claude Code.

Or install shipworthy, the plugin that ships this one along with the rest of its 66 skills, 7 commands, 6 agents, 3 hooks.

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-tracking

README.md
[![agentmods](https://agentmods.dev/badge/skills/vimalk0703/shipworthy/tech-debt-tracking.svg)](https://agentmods.dev/skills/vimalk0703/shipworthy/tech-debt-tracking)
Your own site
<a href="https://agentmods.dev/skills/vimalk0703/shipworthy/tech-debt-tracking"><img src="https://agentmods.dev/badge/skills/vimalk0703/shipworthy/tech-debt-tracking.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 491 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 5.1 $0.00024 $0.00491
Opus 5 $0.00012 $0.00246
Sonnet 5 $0.00005 $0.00098
Haiku 4.5 $0.00002 $0.00049

Measured 6d ago against content hash 1cf19edaa930, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tech-debt-tracking 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 6d 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/operations/tech-debt-tracking/SKILL.md · 58 lines

What it actually says

Tech Debt Tracking

Purpose

Every shortcut has a cost. This skill ensures shortcuts are conscious decisions with documented justifications, not accidents that compound silently.

When to Track

  • Skipping tests for time pressure
  • Using a workaround instead of a proper fix
  • Hardcoding a value that should be configurable
  • Writing a TODO comment
  • Bypassing a quality gate with justification
  • Using a deprecated API or pattern
  • Choosing a quick solution over the correct one

How to Track

Add an entry to .shipworthy/tech-debt.md:

## [Short Description]
- **Date**: YYYY-MM-DD
- **Severity**: low | medium | high | critical
- **Effort to fix**: hours | days | weeks
- **Justification**: Why was this shortcut taken?
- **Impact if not fixed**: What happens if this stays forever?
- **Files affected**: List specific files

Rules

  1. Every shortcut requires justification — "I didn't have time" is a valid justification, but document it
  2. No silent TODOs — every TODO in code must have a corresponding entry in tech-debt.md
  3. Review at session start — the session-start hook surfaces the debt count
  4. Debt has a severity — critical debt should be fixed before adding new features
  5. Debt has a shelf life — if it's been there >30 days with no plan to fix, escalate the conversation

When to Pay Down Debt

  • Before starting a new feature in the same area
  • When the debt is causing real problems (bugs, slowness, confusion)
  • During dedicated refactoring time
  • When the effort to work around the debt exceeds the effort to fix it

Anti-Patterns

  • Tracking debt but never paying it down
  • Not tracking debt at all ("we'll remember")
  • Treating all debt as equal (prioritize by severity and impact)
  • Using debt tracking as an excuse to write sloppy code ("I'll track it as debt")
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. 6d ago First seen · 58 lines · 24 tokens per session scan A 1cf19edaa930

Subscribe to this mod's changes

tech-debt-tracking is a skill published in the GitHub repository Vimalk0703/shipworthy (7 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 491 once invoked, about $0.0001 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

hedgehog-planning-intake

Use on any core for first-run planning intake — Phase 0 runs the vendored BMAD-METHOD planning shelf, shared by every core, and Phase 1 (mining 04-prd.md into intent records plus the Add-ons/sync-and-remote-entities decision) is full-stack-app's and pwa-app's shared procedure — identical mechanics, a different…

skyf0xx/hedgehog · 0 tokens

inbound-triage

Maintainer-only. Use when triaging inbound GitHub issues and pull requests on skyf0xx/hedgehog — "triage the issues", "check the PRs", "review inbound", "what's in the queue". Reads each item read-only, judges it for security and for whether it is real, then fixes and closes or comments and closes. Not part of the…

skyf0xx/hedgehog · 102 tokens

bmad-product-brief

Create, update, or validate a product brief. Use when the user wants help producing, editing, or validating a brief.

skyf0xx/hedgehog · 31 tokens

bmad-revendor

Maintainer-only. Use when re-vendoring vendor-skills/BMAD/ against a newer BMAD-METHOD commit — "update BMAD", "re-vendor BMAD", "bump the BMAD pin". Not part of the Hedgehog discipline a consuming project copies; this only applies to the Hedgehog repo itself.

skyf0xx/hedgehog · 72 tokens

bmad-deep-recon

Decision-grade research, three ways: draft a deep-research prompt for the user to run in their own tool (ChatGPT, Gemini, Grok, Perplexity, …), process a finished research report — file it, distill a succinct cited summary with metadata that downstream skills consume without reprocessing — or run the research here…

skyf0xx/hedgehog · 167 tokens

conventional-commits

Use when uncommitted changes need to be split into atomic, conventional commits ordered for review. Triggers on "commit this", "make commits", "clean up commits", "commit the changes". In Hedgehog, each Loop step is already meant to be its own commit — this skill matters most when a Correction Protocol fast-forward…

skyf0xx/hedgehog · 88 tokens