project
Retrieve project overview, enumerate source files, get task-focused context, check parser readiness, and manage decision journal and doc sync.
Instructions
Code-intelligence (codegraph-compatible) project-intelligence hub. Covers codegraph_metrics (graph-level stats), project overview, file enumeration, smart task-focused context, parser readiness, agent skills/workflow, decision journal, and doc sync in one tool. Pick a capability via action:
PROJECT INFO (read-only):
action=overview — high-level summary of languages, entry points, and architecture. Best first call on an unfamiliar repo. Params: format.
action=files — enumerate source files with filtering. Params: path, extensions, limit, format.
action=smart — S2 task-focused context: surfaces relevant symbols, callers, and files for a task description. Distinct from overview (task-scoped vs whole-project). Params: task, limit.
action=parser — check tree-sitter parser readiness for the project languages. Params: format.
action=tools — verify availability of CLI tools (ripgrep, fd, etc.). Params: (none).
action=metrics — codegraph graph-level statistics (node/edge counts, top hubs, codegraph_metrics equivalent). Params: format.
action=skills — enumerate available agent skills for this project. Params: format.
action=workflow — recommended agent workflow for the current task type. Params: task_type, format.
DECISION + DOC (may write):
action=journal — read or append project decision journal entries. Params: operation, entry, limit.
action=doc_sync — sync documentation to current code state. Params: path, dry_run.
For index lifecycle (status/build/full/auto/sync/cache), use the index facade instead.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | Which capability to invoke. One of: doc_sync, files, journal, metrics, overview, parser, skills, smart, tools, workflow | |
| scope | No | Action discriminator (e.g. point|graph). | |
| mode | No | Action sub-mode (e.g. summary|cycles). | |
| file_path | No | Target file path. | |
| symbol | No | Symbol/function name. | |
| function_name | No | Function name (alias of symbol). | |
| query | No | Search query/pattern. | |
| language | No | Language hint (usually auto). | |
| limit | No | Max results. | |
| output_format | No | Output format (toon|json). |