cldcde: Skill for Claude Code

.claude/skills/debt-sentinel/SKILL.md

debt-sentinel is a skill for Claude Code from aegntic/cldcde. It costs 51 tokens per session (977 once invoked), scanned A, original, MIT.

A code-quality checker that enforces architectural rules while code is being edited. It detects issues such as hardcoded secrets, unsafe SQL construction, direct DOM changes, and several lower-severity patterns.

In plain words
What is it for?
Use it while writing, editing, reviewing, or committing code to block critical violations, log warnings, track debt scores, and check architectural compliance.
Why use it?
It can stop critical problems before they enter the codebase and keeps a record of technical debt, meaning maintenance problems created by shortcuts.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is aegntic/cldcde's own configuration. It tells Claude Code how to work on cldcde itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cldcde configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 /a0/usr/plugins/debt-sentinel/debt-sentinel.py --check <file>.

Reuse

Borrowing it

Nothing to install: this file belongs to aegntic/cldcde. 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/aegntic/cldcde/main/.claude/skills/debt-sentinel/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/aegntic/cldcde

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 debt-sentinel

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/aegntic/cldcde/debt-sentinel"><img src="https://agentmods.dev/badge/skills/aegntic/cldcde/debt-sentinel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 977 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00051 $0.00977
Opus 5 $0.00026 $0.00489
Sonnet 5 $0.00010 $0.00195
Haiku 4.5 $0.00005 $0.00098

Measured 9d ago against content hash 97d18206c14a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

debt-sentinel 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.

.claude/skills/debt-sentinel/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debt-Sentinel: Technical Debt Prevention

Overview

Debt-Sentinel is an architectural enforcer that prevents "vibe coding" slop by blocking anti-patterns before they enter the codebase. It uses PreToolUse hooks to intercept problematic code and maintains a debt ledger for accountability.

When to Use

Activate this skill when:

  • Writing or editing code files
  • Reviewing code for quality issues
  • Checking for security vulnerabilities
  • Validating architectural compliance
  • Before committing changes

Anti-Patterns Detected

Critical (Blocks Edit)

  • Hardcoded Secrets: API keys, passwords, tokens in source code
  • Inline SQL: SQL injection vulnerabilities via string concatenation
  • Direct DOM Manipulation: Bypassing React's virtual DOM

Warning (Logs Debt)

  • Inline Styles: Using style={} instead of CSS classes
  • Console Logging: Using console.log instead of structured logging
  • Magic Numbers: Unnamed numeric literals
  • Service Layer Bypass: Direct HTTP calls bypassing abstractions

Info (Tracked)

  • TODO Without Tickets: Unreferenced TODO comments
  • Poor Naming: Non-descriptive variable names

Usage

Automatic Mode

When integrated with Agent Zero hooks, Debt-Sentinel automatically scans every file edit:

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Edit(*)|Write(*)",
        "command": "python3 /a0/usr/plugins/debt-sentinel/debt-sentinel.py --check"
      }
    ]
  }
}

Manual Mode

# Check a file
python3 /a0/usr/plugins/debt-sentinel/debt-sentinel.py --check <file>

# View session debt report
python3 /a0/usr/plugins/debt-sentinel/debt-sentinel.py --session-end

Understanding Debt Scores

Each violation has an "Interest Rate" (1-10):

  • Critical: 8-10 points
  • Warning: 4-7 points
  • Info: 1-3 points

Session Debt Score accumulates across all edits. High scores trigger cleanup prompts.

Configuration

Edit /a0/usr/plugins/debt-sentinel/ANTI_PATTERNS.md to customize:

Read the full file on GitHub · 144 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 · 144 lines · 51 tokens per session scan A 97d18206c14a

Subscribe to this mod's changes

debt-sentinel is a skill published in the GitHub repository aegntic/cldcde (11 stars, last pushed 13d ago), licensed MIT. It adds 51 tokens to every session and 977 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 2026-08-30.