A codebase scanner that looks for technical debt such as duplicated code, unused code, TODO markers, complex areas, and oversized functions or files.

Use it to review code hygiene, find duplicates or dead code, locate TODOs, and identify large or complex parts of a Python, JavaScript, or TypeScript project.

It makes maintenance problems visible before they accumulate and make future changes harder.

How matteocervelli/llms configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to matteocervelli/llms. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/matteocervelli/llms/main/.claude/skills/techdebt/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/matteocervelli/llms

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/matteocervelli/llms/techdebt.svg)](https://agentmods.dev/skills/matteocervelli/llms/techdebt)

Your own site

<a href="https://agentmods.dev/skills/matteocervelli/llms/techdebt"><img src="https://agentmods.dev/badge/skills/matteocervelli/llms/techdebt.svg" alt="Measured on agentmods" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 686 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.

Model	Per session	Once invoked
Fable 5.1	$0.00064	$0.00686
Opus 5	$0.00032	$0.00343
Sonnet 5	$0.00013	$0.00137
Haiku 4.5	$0.00006	$0.00069

Measured 3d ago against content hash ca520f8430dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

techdebt 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/scan.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/techdebt/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tech Debt Finder

Purpose

Surface technical debt patterns before they accumulate: duplicates, dead code, complexity hotspots, TODOs, oversized files.

Quick Start

/techdebt              # scan current directory
/techdebt src/         # scan specific path
/techdebt --duplicates # only duplicate check
/techdebt --todos      # only TODO/FIXME markers
/techdebt --dead-code  # only dead code

How to Run

Execute the scan script — it auto-detects Python/JS/TS and skips missing tools:

bash $CLAUDE_SKILL_DIR/scripts/scan.sh [path] [filter-flag]

Then interpret and report the output using the Output Format below. The script handles tool invocation; your job is to classify findings by severity and suggest fixes.

Output Format

Produce a # Tech Debt Report with:

Summary table — category, count, severity (Low / Medium / High)
Details per category — file, line, symbol, suggestion
Quick Fixes — any automatable repairs (ruff --fix, eslint --fix)
Recommended Actions — prioritized: Immediate / This week / Backlog

Severity thresholds: duplicates (Low ≤2, Medium 3-5, High >5), dead code (Low ≤5, High >10), large functions (Medium >75 lines, High >100), large files (High >1000 lines), complexity CC >10 (Medium).

Tool Reference

Tools the script uses (installed = runs; missing = skipped with note):

Check	Python	JS/TS
Duplicates	pylint	jscpd
Dead code	vulture	ts-prune
Complexity/size	radon	eslint
Circular imports	pycycle	madge
TODOs	grep (no dep)	grep (no dep)

Install missing tools: uv add --dev vulture radon pylint / npm install -D jscpd ts-prune madge

Gotchas

.venv, node_modules, dist, __pycache__ are auto-excluded by the scan script
pylint --enable=duplicate-code is slow on large codebases; warn if scanning >500 files
ts-prune only works from the project root (needs tsconfig.json); run from a sub-path → 0 findings
radon cc = per-function cyclomatic complexity; radon raw = per-file LOC — different output formats
Deprecated registry dependency check requires ~/.claude/docs/development/registry.yaml; skip silently if absent

Read the full file on GitHub · 66 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/scan.sh 3.6 KB runs code

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.

3d ago First seen · 66 lines · 64 tokens per session scan A ca520f8430dd

Subscribe to this mod's changes

techdebt is a skill published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 64 tokens to every session and 686 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 2026-09-03.

Code review Debugging

adversarial-reviewer

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

emdash-cms/emdash · 71 tokens

gsd-ns-review

Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.

open-gsd/gsd-core · 16 tokens

issue

Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…

jeremylongshore/tons-of-skills-marketplace · 115 tokens

llms: Skill for Claude Code