Matcha:Debt β Development skill for Claude Code
π΅ Technical debt & marker ledger β harvest all // matcha: comments into an actionable report.
How to install Matcha:Debt
Installs to ~/.claude/commands/plumpslabs-matcha-matcha-debt.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/plumpslabs/matcha/HEAD/.claude/commands/matcha:debt.md -o ~/.claude/commands/plumpslabs-matcha-matcha-debt.md Restart Claude Code, or start a new session, for it to be picked up.
What Matcha:Debt does
description: "π΅ Technical debt & marker ledger β harvest all // matcha: comments into an actionable report"
/matcha:debt
**Technical debt & marker ledger.** Harvest all `// matcha:` markers into an actionable report.
Marker Severity Levels
| Marker | Level | Action |
|---|---|---|
// matcha:explain [reason] |
LOW | Logged justification β documented shortcut |
// matcha:todo [task] |
MEDIUM | Future task β schedule or track |
| `// matcha:debt [reason], [fix |
Alternatives in Development
- Remove Comments β Remove Obvious Comments 2.8k β
- Tech Debt Issue β Alias for tech-debt issue 1.2k β
- Comments β /comments Command 849 β
Full documentation available on GitHub
View Source RepositoryRelated Skills
Ponytail Debt
Harvest ponytail: comments into a tracked debt ledger
Tech Debt
Multi-agent technical-debt assessment β fans out region-scoped + specialist hunters, verifies findings, scores
Debt
Scan codebase for technical debt and produce a prioritized report.
Sota Resume
Find and finish the open work in this project β inventory every tracker, checkbox and marker with a controlled
Cairn Setup
Offers the CLAUDE.md marker, then observe-confirm harness generation; --local writes local prefs; --track togg
Code Refactoring Plan
Analyze code smells and technical debt, producing a prioritized refactoring roadmap.
Related Agents
Skill Verify Auditor
Rubric compliance auditor for skill Self-Verify steps (dispatch marker skill-verify: ). Use when a SKILL.md's
Matcha Researcher
Deep-research lead. Plans sub-topics, fans out to scouts, cross-validates claims, synthesizes cited report. Re
Todo Scanner
MUST be used whenever the user asks to find, list, count, or triage TODO/FIXME/HACK/XXX comments (or similar c