Skip to content
Agentmart
Submit a tool

debug

Use when the user asks to debug, diagnose, reproduce, or fix a hard bug, flaky failure, crash, incorrect result, or performance regression.

Skill by kristofferremback

IndexedMIT
Write a review

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/kristofferremback-debug

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

Use when the user asks to debug, diagnose, reproduce, or fix a hard bug, flaky failure, crash, incorrect result, or performance regression.

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/debug

What's inside

Skill name
debug
Description
Use when the user asks to debug, diagnose, reproduce, or fix a hard bug, flaky failure, crash, incorrect result, or performance regression.
License
MIT
Instructions
15 lines in SKILL.md · view on GitHub

Files (3)

  • LICENSE
  • NOTICE.md
  • SKILL.md

SKILL.md (first lines)

# Debug

Build a tight, red-capable feedback loop before implementing a permanent fix. Immediate incident containment may come first, but permanent fixes require evidence.

1. **Feedback loop:** create one fast, deterministic, agent-runnable command that drives the real bug path and can detect the user's exact symptom. For flakes, raise and measure reproduction rate.
2. **Reproduce and minimise:** observe the reported failure, repeat it, then remove inputs and steps one at a time until every remaining part is load-bearing.
3. **Hypotheses:** write 3 to 5 ranked, falsifiable causes with the prediction each makes. Send the list as an AFK-safe milestone, then continue.
4. **Instrument:** test one prediction at a time. Prefer debugger or targeted boundary logs. Tag temporary instrumentation uniquely. Measure performance before changing it.
5. **Fix:** correct the root cause at the smallest complete seam. Do not add a guard that merely silences the symptom.
6. **Regress:** when a correct test seam exists, turn the minimal repro into a failing test before the fix, then watch it pass. Do not add misleading shallow coverage.
7. **Clean:** rerun the original scenario, remove all tagged instrumentation and throwaway harnesses, and state the proven cause.

If no red-capable loop is possible, list what was tried and the missing evidence, access, artifact, or safe instrumentation needed. Do not guess a permanent fix. Never require Kris to operate a terminal-only loop from his phone.

From kristofferremback/slopestyle, MIT.

More from kristofferremback/slopestyle

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 19, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from kristofferremback

Cite this page

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