$ loading_
Find and read Code OSS dev build logs for faster debugging.
The material indicates this is an open-source, prompt-only/documentation-style skill with no required secrets and no declared remote endpoints, so overall risk is low. Its main function is to guide reading local Code OSS dev logs, which may still contain sensitive information and should be handled with minimal exposure.
The material explicitly states that no keys or environment variables are required, and it does not request tokens, API keys, or other credentials, so credential abuse risk is low.
No remote endpoints are declared, and the system flags it as prompt-only; the material only describes local log discovery and reading steps, with no factual indication of sending user data over the network.
This skill is prompt-only/documentation and does not include executable install steps, binaries, or scripts; although the README shows example commands such as ls, tail, and rg, these are instructional text and not evidence that the skill itself executes code.
Its stated purpose is to find and read local Code OSS dev logs, typically under $HOME/.vscode-oss-dev/logs or a custom user-data-dir; these logs may contain sensitive content such as telemetry, network activity, terminal activity, and extension output, so while this is in-scope behavior, data minimization is still important.
The source points to the open-source microsoft/vscode repository on GitHub, making the code auditable and providing strong positive provenance evidence. Although community adoption and maintenance details are limited here, there are no high-risk red flags such as closed-source exfiltration, suspicious install chains, or misleading claims.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "code-oss-logs" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/vscode/main/.github/skills/code-oss-logs/SKILL.md 2. Save it as ~/.claude/skills/code-oss-logs/SKILL.md 3. Reload skills and tell me it's ready
Please find the extension host logs in a Code OSS dev build, identify the most recent error, and summarize the timestamp, key message, and likely cause.
Returns the relevant log location, the latest error snippet, and a brief analysis of the likely cause.
Read the renderer logs from a Code OSS dev build, look for clues about UI lag or errors after startup, and organize them in chronological order.
Outputs key log events in time order and highlights entries that may explain the UI issue.
Please inspect the main process, renderer, and agent host logs in a Code OSS dev build, find correlated clues for the same issue across processes, and provide debugging suggestions.
Generates a cross-log issue summary with correlated evidence and recommended next debugging steps.
Find and display logs from the most recent Code OSS or Agents app dev run.
| App | Default User Data Dir | Logs Path |
|---|---|---|
| Code OSS | $HOME/.vscode-oss-dev | $HOME/.vscode-oss-dev/logs/ |
| Agents app | $HOME/.vscode-oss-dev | $HOME/.vscode-oss-dev/logs/ |
If Code OSS was launched with --user-data-dir=<dir>, use <dir>/logs/ instead of the defaults above. Launch and debugging helpers often create temporary user data dirs under .build/; always prefer the exact user data dir from the launch command when it is known.
Each run creates a timestamped folder like 20260330T163430. The most recent folder sorted by modification time is usually the one the user cares about.
ls -lt "$HOME/.vscode-oss-dev/logs" | head -5
# or for a custom user data dir:
ls -lt "<user-data-dir>/logs" | head -5
tail for recent entries or rg to filter.Each timestamped log folder has this structure:
<timestamp>/
├── main.log # Electron main process (app lifecycle, window management)
├── agenthost.log # Agent host process (Copilot agent, model listing, agent sessions)
├── mcpGateway.log # MCP gateway/server coordination
├── sharedprocess.log # Shared process (extensions gallery, global services)
├── telemetry.log # Telemetry events
├── terminal.log # Terminal/pty activity
├── ptyhost.log # Pty host process
├── network-shared.log # Shared network activity
├── editSessions.log # Edit sessions / cloud changes
├── userDataSync.log # Settings sync
├── remoteTunnelService.log # Remote tunnel service
│
└── window1/ # Per-window logs (window1, window2, etc.)
├── renderer.log # Renderer process (workbench UI, services, startup)
├── network.log # Per-window network activity
├── views.log # View/panel activity
├── notebook.rendering.log # Notebook rendering
├── customizationsDebug.log # Agent customizations debug info (Agents app)
├── mcpServer.*.log # Per-MCP-server logs (one file per configured server)
│
├── exthost/ # Extension host logs
│ ├── exthost.log # Extension host main log (activation, errors)
│ ├── extHostTelemetry.log
│ ├── <publisher.extension>/ # Per-extension log folders
│ │ └── <extension>.log
│ └── output_logging_<timestamp>/ # Extension output channels
│
└── output_<timestamp>/ # Output channel logs (workbench side)
├── tasks.log # Tasks output
├── agentSessionsOutput.log # Agent sessions output (Agents app)
└── agenthost.<clientId>.log # Agent host IPC traffic when tracing is enabled
output_ FoldersA new output_<timestamp>/ folder and a corresponding output_logging_<timestamp>/ inside exthost/ is created each time the window reloads within the same session. The session-level timestamped folder, such as 20260330T163430/, stays the same, but each reload gets fresh output channel directories. The most recent output_* folder by timestamp has the logs for the current or latest reload. Earlier folders contain logs from prior reloads in that session.
| Investigating... | Check these files |
|---|---|
| App startup / crashes | main.log, window1/renderer.log |
| Extension issues | window1/exthost/exthost.log, window1/exthost/<publisher.ext>/ |
…
Validate Azure DevOps pipeline changes and troubleshoot builds and YAML faster.
Generate or update chat customization files for AI coding agents.
Upgrade Anthropic SDKs, migrate versions, and fix dependency or typing issues.
Merge session branch changes back into the base branch cleanly.
Create and maintain screenshot test fixtures for UI components effectively.
Launch VS Code OSS in isolation for automation and multi-process debugging.
Correlate browser activity and dev-server logs to pinpoint issues fast.
Run vscode.dev locally to test the VS Code workbench and Agents window.
Search and analyze past session logs with jq for context and insights.
Give AI coding agents live simulator, browser screenshots, and logs context.
Run and filter integration tests in the VS Code repo confidently.
Run, filter, and debug unit tests in the VS Code repository.