Skip to content
Agentmart
Submit a tool

bug-fix

Use for localized bugs, runtime errors, white screens, failing tests, console errors, and regressions.

Skill by mtvrkan

IndexedMIT★ 10
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/mtvrkan-bug-fix

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 for localized bugs, runtime errors, white screens, failing tests, console errors, and regressions. Make the smallest safe fix.

Reviews

Write a review

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 and code. 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/bug-fix

Tools it pre-approves 6

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

  • Read,
  • Grep,
  • Glob,
  • Bash,
  • Edit,
  • Write

What's inside

Skill name
bug-fix
Description
Use for localized bugs, runtime errors, white screens, failing tests, console errors, and regressions. Make the smallest safe fix.
License
MIT
Allowed tools
Read,, Grep,, Glob,, Bash,, Edit,, Write
Instructions
20 lines in SKILL.md · view on GitHub

Before installing

  • Pre-approves some shell commands

Files (1)

  • SKILL.md

SKILL.md (first lines)

# bug-fix

Read error → root cause → smallest fix → test → done.

1. Read stack trace / error / failing test first. Open ONLY files in the stack trace or directly symptom-related.
2. Fix the smallest responsible code path. Run targeted test — no test exists → add 1 regression test. Non-obvious fix → the why goes in the ROOT line and the commit message, never a code comment.
3. No suspect file in the evidence, or the first fix did not hold → in the main loop switch to `systematic-debug`; inside an agent return `ESCALATE TO: systematic-debug — main loop, [evidence so far]`. Escalate immediately: auth/session/token/payment → security-guard | DB corruption/schema/migration → db-guard.

Deep reference: `${CLAUDE_PLUGIN_ROOT}/agent_docs/error-handling-patterns.md` — typed error hierarchies, boundary handling, retry/fallback patterns.

## Output

```text
ROOT: [what and where]
FIX: [file:line — what changed]
TEST: [command — ✓ | regression test added]
RISK: low | medium
```

From mtvrkan/senior-dev-kit, MIT.

More from mtvrkan/senior-dev-kit

Signals

Stars
10
Forks
0
Open issues
0
Last commit (this folder)
Oct 5, 2026 (23 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/mtvrkan/senior-dev-kit
Website
senior.mtvrkan.com/
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from mtvrkan

Cite this page

bug-fix skill. Agent Mart. https://agentmart.dev/skills/mtvrkan-bug-fix (last updated 2026-10-24)