Graph Build
Build or refresh a local SQLite code knowledge graph so your agent can search structure and trace blast radius before risky edits.
Overview
Graph-build is an agent skill most often used in Build (also Ship, Operate) that builds or updates a tree-sitter SQLite code knowledge graph at `.gauntlet/graph.db` for search and blast-radius analysis.
Install
npx skills add https://github.com/athola/claude-night-market --skill graph-buildWhat is this skill?
- Full or incremental builds of `.gauntlet/graph.db` via `graph_build.py`
- 20+ languages parsed into File, Class, Function, Type, and Test nodes
- Edges for CALLS, IMPORTS_FROM, INHERITS, CONTAINS, IMPLEMENTS, and TESTED_BY
- JSON report with files parsed, nodes, edges, and duration
- Suggests graph search and blast-radius analysis as follow-ups
- 20+ languages supported
- 5 node types (File, Class, Function, Type, Test)
- 6 edge relationship kinds
Adoption & trust: 1 installs on skills.sh; 304 GitHub stars; 3/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
You need to change or debug a large repo but lack a machine-readable map of files, symbols, and call relationships.
Who is it for?
Multi-language codebases where you run agent sessions that depend on call graphs, imports, and test linkage before editing.
Skip if: Repos where you only need a one-off file read, have no Python 3 available to run the script, or do not use the Gauntlet graph workflow.
When should I use this skill?
Setting up the graph before search or blast-radius analysis; at session start; after significant code changes; when the user asks about codebase structure.
What do I get? / Deliverables
You get an up-to-date `.gauntlet/graph.db` with parsed node and edge counts so you can run graph search or blast-radius analysis on confident structural context.
- .gauntlet/graph.db knowledge graph
- JSON build summary (files, nodes, edges, duration)
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Build because the deliverable is agent-side structural indexing of the repo, not shipping or growth work. Agent-tooling fits tree-sitter graph generation that powers search, flow tracing, and blast-radius skills in the same toolkit.
Where it fits
Run a full graph build at session start so the agent knows class and call topology before implementing a feature.
Incremental rebuild after a large PR so review skills see updated CALLS and TESTED_BY edges.
Refresh the graph after production hotfixes to keep blast-radius answers aligned with the live tree.
How it compares
Use this structured graph build instead of asking the agent to grep and guess relationships file by file.
Common Questions / FAQ
Who is graph-build for?
Solo and indie builders using Claude Code or similar agents on real codebases who want AST-backed structural maps before search or impact analysis.
When should I use graph-build?
At session start for awareness, after significant code changes, before blast-radius or flow tracing, or when you ask how the codebase is organized—in Build agent-tooling and again in Ship review or Operate iteration when structure drifted.
Is graph-build safe to install?
It runs a local Python build script against your project tree; review the Security Audits panel on this Prism page and inspect `graph_build.py` before running on sensitive repos.
SKILL.md
READMESKILL.md - Graph Build
# Build Code Knowledge Graph Build or update the `.gauntlet/graph.db` knowledge graph for the current codebase. ## Steps 1. **Detect target**: Use the current working directory or a user-specified path. 2. **Check for existing graph**: If `.gauntlet/graph.db` exists, run an incremental update. Otherwise, run a full build. 3. **Run the build script**: For full build: ```bash python3 ${CLAUDE_PLUGIN_ROOT}/scripts/graph_build.py <dir> ``` For incremental update: ```bash python3 ${CLAUDE_PLUGIN_ROOT}/scripts/graph_build.py <dir> --incremental ``` 4. **Report results**: Show the JSON output including files parsed, nodes created, edges created, and duration. 5. **Suggest next steps**: Recommend searching the graph or running blast radius analysis. ## When To Use - At the start of a session to build structural awareness - After significant code changes to update the graph - Before running blast radius analysis or flow tracing - When the user asks about codebase structure ## What Gets Parsed The graph extracts nodes (File, Class, Function, Type, Test) and edges (CALLS, IMPORTS_FROM, INHERITS, CONTAINS, IMPLEMENTS, TESTED_BY) from 20+ languages including Python, JavaScript, TypeScript, Go, Rust, Java, C/C++, Ruby, and PHP. ## Storage - Database: `.gauntlet/graph.db` (SQLite with WAL mode) - Auto-creates `.gauntlet/.gitignore` to prevent commits - Incremental updates use SHA-256 hashing to skip unchanged files