ide-debug

ide-debug is a skill for Claude Code, Codex from Oolab-labs/claude-ide-bridge. It costs 47 tokens per session (772 once invoked), scanned A, original, MIT.

A debugging workflow that combines tests, breakpoints, debugger expressions, code changes, and verification.

In plain words
What is it for?
It is for running tests, stopping execution at selected conditions, inspecting program values, applying fixes, and confirming the result.
Why use it?
It takes you from a failing test or runtime problem toward its underlying cause and a checked fix.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/oolab-labs/claude-ide-bridge/ide-debug
Any agent
npx skills add Oolab-labs/claude-ide-bridge --skill ide-debug
Clone the repo
git clone --depth 1 https://github.com/Oolab-labs/claude-ide-bridge

Made for: Claude Code, Codex.

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/claude-ide-bridge/ide-debug.svg)](https://agentmods.dev/skills/oolab-labs/claude-ide-bridge/ide-debug)
Your own site
<a href="https://agentmods.dev/skills/oolab-labs/claude-ide-bridge/ide-debug"><img src="https://agentmods.dev/badge/skills/oolab-labs/claude-ide-bridge/ide-debug.svg" alt="Measured on agentmods" 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. Scan, not verified.
Origin original No closer match found 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 $0.00047 $0.00772
Opus 5 $0.00023 $0.00386
Sonnet 5 $0.00009 $0.00154
Haiku 4.5 $0.00005 $0.00077

Measured 5d ago against content hash ca446232688b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 5d 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

Copies of this mod

1 near-identical copy found in the catalogue:

  • ide-debug — 100% identical, 0 lines differ
.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. 5d 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/claude-ide-bridge (38 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 772 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

plugin-guide-maintenance

Keep the Plugin Guide aligned with public Plugin SDK changes that affect its documented contract. Use this skill when an addition, change, rename, stabilization, or removal in @get-bb/plugin-sdk, app.slots., or BbPluginApi changes a Guide card, API symbol list, fixture, or SDK inventory. Do not use it for internal API…

get-bb/bb · 85 tokens

memory

Use durable BB memory when prior project knowledge or cross-project user preferences can improve the current task, and save durable new learning through the bb memory CLI.

get-bb/bb · 32 tokens

workflows

Execute a workflow script that orchestrates multiple subagents deterministically. Use when the user explicitly requests a workflow, multi-agent orchestration, parallel or sequential agent pipelines, structured agent outputs, or a durable background workflow run.

get-bb/bb · 47 tokens

submit-a-plugin

Submit a bb plugin to the BB Community marketplace. Use whenever a user asks to submit, list, publish, or add a plugin to the BB marketplace, or asks for a marketplace pull request. This skill validates the plugin and release, creates the marketplace entry and icon, and opens the pull request.

get-bb/bb · 64 tokens

secrets

Securely request API keys, access tokens, passwords, webhook secrets, or other credentials and write them to a dotenv file without exposing their values to the agent. Use whenever a task needs a credential that the user must supply.

get-bb/bb · 48 tokens

canvas

Author Nimbalyst Project Canvas boards (.canvas files) — an infinite canvas whose cards are live editors for real workspace files and shared documents, arranged spatially and wired with edges. Use when the user asks for a canvas, a board, a spatial layout of documents or mockups, a flow of screens, or a workspace…

nimbalyst/nimbalyst · 69 tokens