graph-query

name	graph-query
description	PROACTIVELY query the code graph BEFORE modifying any component. Use it to find callers, dependencies, and the blast radius of a change so you do not break something you did not read. Also use when the user asks "find callers", "check dependencies", "what uses this", or when exploring an unfamiliar codebase. Check the graph before editing, not after something breaks.
allowed-tools	Bash
compatibility	Requires AI Maestro (aimaestro.dev) with Bash shell access
metadata	{"author":"23blocks","version":"1.0.0"}

AI Maestro Code Graph Query

CRITICAL: AUTOMATIC BEHAVIOR - READ THIS FIRST

THIS IS NOT OPTIONAL. THIS IS YOUR DEFAULT BEHAVIOR.

Every time you use the Read tool on a code file, you MUST IMMEDIATELY query the graph to understand:

• What is this component/function?
• What depends on it? (callers, serializers, child classes)
• What does it depend on? (callees, parent classes, associations)

DO NOT:

• Wait for the user to ask you to query the graph
• Skip the graph query because "it seems simple"
• Assume you understand the impact without checking
• Make changes before understanding dependencies

ALWAYS:

• Query the graph IMMEDIATELY after reading any code file
• Query BEFORE making any modifications
• Query when you find files via search (grep/glob)
• Include graph findings in your analysis to the user

The Rule: Read File → Query Graph → Then Proceed

1. You read a file with Read tool
2. IMMEDIATELY run graph queries (describe, find-callers, find-serializers, etc.)
3. NOW you understand the full context
4. NOW you can analyze, modify, or discuss the code

Example - Reading a Model:

# After reading app/models/user.rb, IMMEDIATELY run:
graph-describe.sh User
graph-find-serializers.sh User
graph-find-associations.sh User

Example - Reading a Function:

# After reading a file with process_payment function, IMMEDIATELY run:
graph-find-callers.sh process_payment
graph-find-callees.sh process_payment

---

Available Commands

All commands auto-detect your agent ID from the tmux session. Just run them:

Query Commands

Command	Description
graph-describe.sh <name>	Describe a component or function
graph-find-callers.sh <function>	Find all functions that call this function
graph-find-callees.sh <function>	Find all functions called by this function
graph-find-related.sh <component>	Find related components (extends, includes, etc.)
graph-find-by-type.sh <type>	Find all components of a type (model, controller, etc.)
graph-find-serializers.sh <model>	Find serializers for a model
graph-find-associations.sh <model>	Find model associations (belongs_to, has_many)
graph-find-path.sh <from> <to>	Find call path between two functions

Indexing Commands

Command	Description
graph-index-delta.sh [project-path]	Delta index - only re-index changed files

Delta Indexing (New)

When files change in your codebase, use delta indexing to quickly update the graph:

# Delta index - only process changed files
graph-index-delta.sh

# Delta index a specific project
graph-index-delta.sh /path/to/project

First Run Behavior:

• First time: Does a full index + initializes file tracking metadata
• Subsequent runs: Only indexes new/modified/deleted files

Note: There is no separate graph-index.sh script. graph-index-delta.sh handles both full indexing (on first run) and incremental updates (on subsequent runs).

Output shows:

• New files added
• Modified files re-indexed
• Deleted files removed
• Unchanged files skipped

Performance:

• Full index: 30-120 seconds (1000+ files)
• Delta index: 1-5 seconds (5-10 changed files)

What to Query Based on What You Read

File Type	IMMEDIATELY Query
Model	graph-describe.sh, graph-find-serializers.sh, graph-find-associations.sh
Controller	graph-describe.sh, graph-find-callees.sh
Service	graph-describe.sh, graph-find-callers.sh
Function	graph-find-callers.sh, graph-find-callees.sh
Serializer	graph-describe.sh
Any class	graph-find-related.sh

Why This Matters

Without querying the graph, you will:

• Miss serializers that need updating when you change a model
• Break callers when you change a function signature
• Miss child classes that inherit your changes
• Overlook associations that depend on this model

The graph query takes 1 second. A broken deployment takes hours to fix.

Component Types

Use with graph-find-by-type.sh:

• model - Database models
• serializer - JSON serializers
• controller - API controllers
• service - Service objects
• job - Background jobs
• concern - Shared modules
• component - React/Vue components
• hook - React hooks

Helper Scripts

This skill relies on an internal helper script that provides shared utility functions:

• graph-helper.sh - Sourced by the graph-*.sh tool scripts. Provides graph-specific API functions (graph_query, init_graph) and initialization logic. Located alongside the tool scripts in ~/.local/bin/ (installed) or plugin/src/scripts/ (source). If tool scripts fail with "common.sh not found", re-run the installer (~/ai-maestro/install-graph-tools.sh).

Error Handling

Script not found:

• Check PATH: which graph-describe.sh
• Verify scripts installed: ls -la ~/.local/bin/graph-*.sh
• Scripts are installed to ~/.local/bin/ which should be in your PATH
• If not found, run the installer from the AI Maestro project root: ~/ai-maestro/install-graph-tools.sh

API connection fails:

• Ensure AI Maestro is running: curl http://127.0.0.1:23000/api/hosts/identity
• Ensure your agent is registered (scripts auto-detect from tmux session)
• Check exact component names (case-sensitive)

Graph is unavailable:

• Inform the user: "Graph unavailable, proceeding with manual analysis - increased risk of missing dependencies."

Installation

If commands are not found, run the installer from the AI Maestro project root:

~/ai-maestro/install-graph-tools.sh

This installs scripts to ~/.local/bin/.