patchwork-os: Skill for Claude Code

.claude/skills/ide-debug/SKILL.md

ide-debug is a skill for Claude Code from Oolab-labs/patchwork-os. It costs 47 tokens per session (772 once invoked), scanned A, a copy of ide-debug, MIT.

A guided debugging workflow that connects an IDE, test runner, and debugger. An IDE is the code editor where you can set breakpoints and inspect running code.

In plain words
What is it for?
Use it to investigate failing tests or runtime problems, identify their root causes, apply fixes, and confirm the tests pass.
Why use it?
It brings failure finding, breakpoint setup, expression evaluation, fixes, and verification into one process instead of requiring separate manual steps.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

This is Oolab-labs/patchwork-os's own configuration. It tells Claude Code how to work on patchwork-os 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 patchwork-os configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Oolab-labs/patchwork-os. 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/Oolab-labs/patchwork-os/main/.claude/skills/ide-debug/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Oolab-labs/patchwork-os

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 ide-debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/oolab-labs/patchwork-os/ide-debug/github.svg)](https://agentmods.dev/skills/oolab-labs/patchwork-os/ide-debug)
Your own site
<a href="https://agentmods.dev/skills/oolab-labs/patchwork-os/ide-debug"><img src="https://agentmods.dev/badge/skills/oolab-labs/patchwork-os/ide-debug/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 ide-debug

Your own site · 80×15
<a href="https://agentmods.dev/skills/oolab-labs/patchwork-os/ide-debug"><img src="https://agentmods.dev/badge/skills/oolab-labs/patchwork-os/ide-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 772 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.
Origin 100% copy Near-identical to another mod 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 $0.00047 $0.00772
Opus 5.5 $0.00019 $0.00309
Sonnet 5.5 $0.00009 $0.00154
Haiku 4.5 $0.00005 $0.00077

Measured 1mo ago against content hash ca446232688b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ide-debug 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 1mo 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.

Origin

This is a copy

100% identical to ide-debug — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/ide-debug/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IDE Debug Workflow

Prerequisites

  1. Check if the getToolCapabilities MCP tool is available to you.
    • Not available (no MCP tool by that name): stop and tell the user: "This skill requires the Claude IDE Bridge with a connected VS Code extension. It uses debug tools (breakpoints, debugger evaluation, debug state) that have no CLI equivalent.

      To use this skill:

      1. Start the bridge: npm run start-all (in claude-ide-bridge/)
      2. Ensure the Claude IDE Bridge extension is installed in your IDE
      3. Use the claude --ide session (not remote-control)

      Alternative: run tests directly via npm test to identify failures."

    • Available: call it. If extensionConnected is false: show the same message. If true: proceed.

Run a complete debug cycle using the IDE bridge's debug and test tools. This workflow automates what would normally require switching between terminal, editor, and debugger.

Workflow

Phase 1: Identify the failure

  1. Run tests using runTests with the provided filter argument: $ARGUMENTS
    • If no argument provided, run the full test suite
  2. If all tests pass, report success and stop
  3. For each failure, note the file, line, test name, and error message

Phase 2: Set up debugging

  1. For the first failing test, use goToDefinition or openFile to navigate to the failing code
  2. Use getDocumentSymbols on the test file to understand the test structure
  3. Use setDebugBreakpoints to set a breakpoint at the assertion line or the line referenced in the error
    • Use conditional breakpoints when the error message suggests a specific condition

Phase 3: Inspect runtime state

  1. Use startDebugging with the appropriate debug configuration
    • For vitest/jest: look for "Vitest" or "Jest" debug configs
    • For pytest: look for "Python" debug configs
  2. When the breakpoint hits, use evaluateInDebugger to inspect:
    • The variables mentioned in the error message
    • The expected vs actual values
    • Any intermediate computation results
  3. Use getDebugState to examine the full call stack and scope variables
  4. Use stopDebugging once you've identified the root cause

Read the full file on GitHub · 74 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. 1mo ago First seen · 74 lines · 47 tokens per session scan A ca446232688b

Subscribe to this mod's changes

ide-debug is a skill published in the GitHub repository Oolab-labs/patchwork-os (31 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 772 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to ide-debug, differing in 0 lines, and is treated as a copy.