Summarize a file, folder, or repo. Use action=path|repo. Prefer compact mode to keep context small.

Find tools by category/capability. Check callable+requiredArgs before invoking. Use include_examples only when needed.

Health/diagnostics. Healthy when any backend is available. format=dense gives compact status. includeDetails adds routing/cache stats and redacted errors.

Autonomous multi-step task runner. Use readOnly for analysis. Defaults: maxSteps=50, maxActionsPerStep=100; use async for long tasks.

Manage CLI orchestration settings. Use simulate for read-only routing prediction; use logs for runtime routing evidence.

Execute tasks via OpenCode/Copilot orchestration. Requires orchestration enabled.

Workspace metadata/snapshot/explore helper. Use for quick structure discovery before deeper tools.

Find or implement TODO/FIXME markers with prioritization options.

Answer repo-level questions using indexed context and local LLM.

Estimate missing tests from source/test patterns (requires root). Supports relative-path globs; defaults include TS/JS/PY. Guidance only.

Estimate ripple effects of changed files across dependencies, imports, and tests.

Build in-memory symbol index for cross-file lookups.

Trace import/export links from entry points.

Security actions: scan, risk, redact, fix. scan may return coverage guidance for narrow scope; use recommended include globs and includeHidden=true.

Run lints, syntax validation, or LLM-assisted lint fixes.

Run formatter or LLM-assisted syntax fixes.

LLM analysis for one file. If path is a directory, returns candidate-file hints. includeContent defaults to false.

Unified search (intelligent|structured|gather|filenames). root defaults to "." when omitted.

Privacy-preserving code review (security/performance/style/comprehensive). Hidden files require includeHidden=true.

Generate docs (jsdoc/readme/api/examples) for a file or folder.

Suggest refactors with tradeoffs and safer alternatives.

Propose targeted code edits from intent. apply=true auto-applies only high-confidence edits.

Search -> analyze -> suggest/apply fixes for repeated patterns across files.

Generate a new file draft from intent and local patterns. Does not write files.

Generate AGENTS.md from project structure. useLlm=false for faster static output.

Detect similar files/functions/code spans with similarity thresholds.

Run multi-signal quality checks: duplicates, complexity, smells, security.

Explain, optimize, or simplify code snippets.

Explain regex or generate regex from natural language.

Naming suggestions and extraction hints for selected code.

Summarize code diffs into concise human-readable changes.

Explain stack traces/errors and likely fixes.

Translate code between languages with structure preservation.

Turn a feature request into concrete implementation steps.

Estimate Big-O complexity with optional detail.

Condense logs and highlight likely root causes.