greppable

Search all 7 GDL layers for a topic with cross-layer formatted output. Use for quick lookups across the knowledge base.

Create a new GDLD architecture diagram from current conversation context — flows, patterns, sequences, gotchas

Full codebase scan — generates code maps, architecture diagrams, and conditional schema maps and API contracts. Token-intensive, runs as subagent.

Manage .gdlignore exclusion patterns — add, remove, list, or detect patterns to exclude from GDL bridge scanning

Toggle automatic session memory extraction on or off — shows current status and updates greppable.local.md config

Set up or update greppable configuration for this project — creates config, directory structure, and .gitignore entries

Generate GDL pull request summary with change-flow diagram — use when PR is created or merged. Posts Mermaid to GitHub.

Check GDL health and diagnose issues — platform diagnostics, root resolution, setup status, scope conflicts, artifact inventory, and interactive investigation tools

Use when working with API endpoints, understanding what a service exposes, or checking API authentication and parameters before integrating. Works with .gdla API contract files — endpoint lookups, schema definitions, auth configuration, and cross-API dependencies. Triggers on: "what endpoints does X expose", "what auth does Y require", "what parameters does this endpoint accept", integrating with a service's API, or direct .gdla file operations. NOT for building new API endpoints from scratch, creating OpenAPI specs, or .gdls schema maps.

Use when excluding files or directories from GDL scanning — generated code, node_modules, UI component libraries, or test fixtures that pollute code maps. Triggers on: 'ignore this directory', 'exclude from scanning', 'too much noise in GDL', '.gdlignore'. NOT for .gitignore management or general file filtering.

Use when creating, reviewing, or maintaining @rule records in rules.gdl files — provides format reference, quality criteria for what makes a rule worth writing, severity calibration, and the gdl_rules_for_file helper. Triggers on: rules.gdl files, 'add a rule', 'create a coding rule', 'enforce this convention', observing a strong codebase convention. NOT for @memory observations, .gdlm files, or general code review.

Use when exploring codebase structure or understanding module dependencies using the .gdlc file-level code index — finding which file exports a symbol, tracing import relationships, or getting oriented in an unfamiliar codebase. Triggers on: "where is X defined", "what depends on Y", "show me the project structure", getting an overview of the codebase, finding files by directory or language, or direct .gdlc file operations. NOT for reading or searching source code implementations, running bridge tools (src2gdlc), .gdls schema maps, or .gdla API contracts.

Use when working with structured business data records — orders, invoices, products, or any @type records in .gdl files. Covers: filtering records by field values, aggregating data by region/status/category, cross-referencing between record types, extracting specific fields, or converting GDL data to CSV/JSON. Triggers on: "show me all orders over X", "filter by status", "aggregate by region", business data queries, or direct .gdl file operations. NOT for SQL database queries, .gdls schema maps, or .gdlm memory files.

Use when creating, modifying, or querying .gdld diagram files — architecture flows, sequence diagrams, service topology, and gotcha/anti-pattern records. Also triggers when: investigating how services connect, understanding request flows or data pipelines, assessing blast radius of a change, "how does X connect to Y", "what calls what", "show me the flow", or documenting what NOT to do. NOT for .gdls schema maps — .gdld and .gdls are different formats.

Use when agent memory from prior sessions could inform current work — choosing between alternatives when past decisions exist, investigating why something was built a certain way, or checking if a problem was already solved. Triggers on: "what did we decide about X", "why did we choose Y", "what do we know about Z", references to past session work ("last time", "before", "we decided"), recording decisions/observations/errors, correcting memories, following supersedes chains, concept anchors, or any .gdlm file operation. NOT for general "remember my preferences", git log/blame searches, episodic conversation memory, PR comment reviews, or meeting notes in docs/.

REQUIRED before ANY .gdlc, .gdlm, .gdld, .gdls, .gdla, or .gdl file operation. Also triggers on structural questions about code, past decisions, service architecture, or data: 'what did we decide about X', 'how is Y structured', 'what depends on Z', 'what endpoints does W expose', exploring unfamiliar code areas, or choosing between implementation alternatives. This project has pre-indexed knowledge that answers these in one grep. NOT for pure implementation tasks like writing functions, fixing bugs, or styling.