Skip to content
Agentmart
Submit a tool

debt

Run a technical debt audit — TODOs, deprecated patterns, complex functions, outdated dependencies.

Skill by krone9

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying debt?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/krone9-debt

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Run a technical debt audit — TODOs, deprecated patterns, complex functions, outdated dependencies. Saves prioritised list to docs/debt.md. Use when the user types /debt or asks for a technical debt review.

Use cases: security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/debt

Tools it pre-approves 8

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Read,
  • Bash(grep:*),
  • Bash(find:*),
  • Bash(npm
  • outdated:*),
  • Bash(pip
  • list:*),
  • Write

What's inside

Skill name
debt
Description
Run a technical debt audit — TODOs, deprecated patterns, complex functions, outdated dependencies. Saves prioritised list to docs/debt.md. Use when the user types /debt or asks for a technical debt review.
License
MIT
Allowed tools
Read,, Bash(grep:*),, Bash(find:*),, Bash(npm, outdated:*),, Bash(pip, list:*),, Write
Instructions
75 lines in SKILL.md · view on GitHub

Before installing

  • Pre-approves some shell commands

Files (1)

  • SKILL.md

SKILL.md (first lines)

## Task: Technical debt audit

Scan the codebase for technical debt and produce a prioritised list. Report only — do not fix anything until the user confirms.

### Pass 1: TODOs and deferred work
```bash
grep -rn "TODO\|FIXME\|HACK\|XXX\|TEMP\|KLUDGE\|@deprecated" \
  src/ --include="*.ts" --include="*.js" --include="*.py" --include="*.go"
```
Group by type. Note how long each has been there if determinable from git blame.

### Pass 2: Complexity
Find functions that are likely too complex:
- Functions over 50 lines
- Files over 300 lines
- Deeply nested conditionals (4+ levels)
- Functions with more than 5 parameters

```bash
find src/ -name "*.ts" -o -name "*.js" -o -name "*.py" | xargs wc -l | sort -rn | head -20
```

### Pass 3: Outdated dependencies
Check for outdated packages:
- Node: `npm outdated` or `yarn outdated`
- Python: `pip list --outdated`
- Go: `go list -u -m all`

Flag anything that is more than 2 major versions behind, or has known security advisories.

### Pass 4: Deprecated patterns
Look for:
- Deprecated API usage (marked with `@deprecated` or known deprecated methods)
- Old syntax that should have been migrated (e.g. `var` instead of `const/let`, callbacks instead of async/await)
- Test files with skipped/commented-out tests (`it.skip`, `xtest`, `@pytest.mark.skip`)
- Dead feature flags or config values that are never toggled

### Pass 5: Missing fundamentals
Check for:
- No tests for key modules (find test files, cross-reference against src files)
- No error handling in async functions
- Console.log / print statements left in production code
- Commented-out code blocks (more than 5 lines)

### Output the debt report

```
## Technical Debt Audit — [date]

### 🔴 High Priority
- [item] — [why it matters] — [estimated effort: S/M/L]

### 🟠 Medium Priority
- [item] — [why it matters] — [estimated effort: S/M/L]

### 🟡 Low Priority / Housekeeping
- [item]

### TODOs by age
[list TODOs with approximate age if determinable]

### Outdated dependencies
[table: package, current version, latest version, risk level]

### Summary
Total debt items: [n] | High: [n] | Medium: [n] | Low: [n]
Estimated total effort: [S/M/L/XL]
```

### Save
Write to `docs/debt.md`. Append with date header if file exists — debt should be tracked over time.

Report: "✅ Debt audit written to docs/debt.md"

From krone9/pi-superpowers, MIT.

More from krone9/pi-superpowers

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
May 5, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from krone9

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get debt running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying debt?

CallGet help
Cite this page

debt skill. Agent Mart. https://agentmart.dev/skills/krone9-debt (last updated 2026-10-24)