graph-build

name	graph-build
description	[Code Intelligence] Use when you need to build, update, or sync the code review knowledge graph. Flag: --scope={full|update|sync} (default auto-detect); --scope=full forces a full rebuild, --scope=update re-parses uncommitted working-tree changes, --scope=sync syncs committed git changes then updates the working tree.

Codex compatibility note:

• Invoke repository skills with $skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.
• Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.
• User-question prompts mean to ask the user directly in Codex.
• Ignore Claude-specific mode-switch instructions when they appear.
• Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.
• Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.
• Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.
• For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.
• If a required step/tool cannot run in this environment, stop and ask the user before adapting.

Codex Project-Reference Loading (No Hooks)

Codex uses static project-reference loading instead of runtime-injected project docs. When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.

Always read:

• docs/project-config.json (project-specific paths, commands, modules, and workflow/test settings)
• docs/project-reference/docs-index-reference.md (routes to the full docs/project-reference/* catalog)
• docs/project-reference/lessons.md (always-on guardrails and anti-patterns)

Missing/stale context route: If docs/project-config.json, the docs index, lessons.md, CLAUDE.md, AGENTS.md, or any task-required reference doc is missing or stale, auto-run $project-init or the narrow setup route ($project-config, $docs-init, $scan-all, $scan --target=<key>, $claude-md-init) before ordinary project-specific work. If Codex mirrors or AGENTS.md are missing/stale, ask the user to run $sync-codex; do not auto-run it.

Situation-based docs:

• Backend/CQRS/API/domain/entity changes: backend-patterns-reference.md, domain-entities-reference.md, project-structure-reference.md
• Frontend/UI/styling/design-system: frontend-patterns-reference.md, scss-styling-guide.md, design-system/README.md
• Spec authoring, docs/specs/ pathing, or TC format: feature-spec-reference.md, spec-system-reference.md, spec-principles.md
• Behavior/public-contract changes or spec-test-code sync: workflow-spec-test-code-cycle-reference.md plus the spec docs above
• Derived spec indexes/ERDs/reimplementation guides: spec-system-reference.md and source Feature Specs under docs/specs/
• Integration test implementation/review: integration-test-reference.md
• E2E test implementation/review: e2e-test-reference.md
• Code review/audit work: code-review-rules.md plus domain docs above based on changed files

Do not read all docs blindly. Start from docs-index-reference.md, then open only relevant files for the task.

Quick Summary

Goal: [Code Intelligence] Build, update, or sync the code review knowledge graph. Parses codebase with Tree-sitter into a structural graph (functions, classes, imports, calls, tests) stored in SQLite. Enables blast-radius analysis and graph-powered code review. --scope selects the lifecycle operation — full (rebuild), update (working-tree changes; folds former /graph-update), sync (committed git changes + working-tree update; folds former /graph-sync) — default auto-detects from graph status.

Workflow:

1. Detect — classify request scope and target artifacts.
2. Execute — apply required steps with evidence-backed actions.
3. Verify — confirm constraints, output quality, and completion evidence.

Key Rules:

• Scope flag (see Scope Mode): default (no flag) auto-detects via status (full if never built, else incremental); --scope=full forces rebuild; --scope=update = uncommitted working-tree changes (CLI update, folds /graph-update); --scope=sync = committed git changes then working-tree update (CLI sync + update, folds /graph-sync).
• MUST ATTENTION keep claims evidence-based (file:line) with confidence >80% to act.
• MUST ATTENTION keep task tracking updated as each step starts/completes.
• NEVER skip mandatory workflow or skill gates.

Prerequisites

Requires Python 3.10+ with: pip install tree-sitter tree-sitter-language-pack networkx

Scope Mode (--scope=)

--scope	CLI verb(s)	What it does	Former skill
(none, default)	status → build or update	Auto-detect: full build if never built, else incremental update	—
full	build --json	Force full rebuild (ignore existing graph)	—
update	update --json	Re-parse uncommitted working-tree changes (staged/unstaged)	/graph-update
sync	sync --json then update --json	Sync committed git changes (last_synced_commit → HEAD), then working tree	/graph-sync

Default (no --scope) auto-detects from status. update = working-tree changes (base HEAD~1, options --base/--repo). sync = committed changes + chained working-tree update (the sync→update chain is preserved). Session-start auto-sync runs the CLI sync directly via the graph-session-init hook — independent of this skill. Pick --scope FIRST (default auto-detect), then run the matching branch.

Steps

Default (auto-detect) — build or incremental update

1. Check availability — Run via Bash:

   python .claude/scripts/code_graph status --json
   

   • If error (Python/deps missing): show install instructions and stop
   • If last_updated is null: graph never built → proceed with full build
   • If last_updated exists: graph exists → proceed with incremental update

2. Build or update — Run via Bash:

   • Full build: python .claude/scripts/code_graph build --json
   • Incremental: python .claude/scripts/code_graph update --json

3. Report results from JSON output:

   • Files parsed, nodes created, edges created
   • Languages detected
   • Any errors encountered
   • Build type (full vs incremental)

--scope=full — force full rebuild

python .claude/scripts/code_graph build --json

Always does a complete reparse (ignores existing graph). Report: files parsed, nodes/edges created, languages, build type.

--scope=update — uncommitted working-tree changes (folds /graph-update)

python .claude/scripts/code_graph update --json

Diffs the working tree against a base commit (default HEAD~1), re-parses changed/added files, removes deleted files from the graph, then re-runs the API + implicit connectors. Options: --base <commit> (default HEAD~1), --repo <path>. Report: files updated/added/deleted, or "Working tree clean — graph already up to date".

--scope=sync — committed git changes + working tree (folds /graph-sync)

1. Sync committed changes via Bash:

   python .claude/scripts/code_graph sync --json
   

   Diffs last_synced_commit → HEAD, re-parses changed/added files, removes deleted files, re-runs connectors, stores new HEAD. If it reports full_rebuild_fallback (unreachable commit after rebase/force-push), a full rebuild was triggered — inform the user.

2. Update working tree (chained — former graph-sync step 4) via Bash:

   python .claude/scripts/code_graph update --json
   

3. Report: files synced/added/modified/deleted, then working-tree update results (or "working tree clean").

sync vs update: sync detects committed changes only (last_synced_commit → HEAD; use after pull/merge/checkout). update detects working-tree changes (staged/uncommitted, mid-session). No --files flag on sync/update (auto-detected from git); there is no incremental subcommand (use update).

When to Use

• First time setting up graph for a project
• After major refactoring or branch switches
• If graph seems stale or out of sync
• Graph auto-updates via PostToolUse hook, so manual builds are rarely needed

Notes

• Graph stored at .code-graph/graph.db (SQLite, auto-gitignored)
• Supported: Python, TypeScript, JavaScript, Vue, Go, Rust, Java, C#, Ruby, Kotlin, Swift, PHP, Solidity, C/C++
• Initial build: ~10s for 500 files. Incremental: <2s

Connectors (Auto-Run)

After build/update, graph connectors run automatically if configured in project-config.json:

• API Endpoints: Frontend HTTP calls matched to backend routes (graphConnectors.apiEndpoints)
• Implicit Connections: Entity events, message bus, command events (graphConnectors.implicitConnections)

See $graph-connect-api and .claude/docs/code-graph-mechanism.md for details.

DB Performance Indexes

The graph database includes optimized indexes created automatically on first build:

• idx_nodes_name — fast node name lookups for search
• idx_edges_kind_source — composite index for filtered edge queries (kind + source)
• idx_edges_kind_target — composite index for filtered edge queries (kind + target)

These indexes are defined in the init schema and auto-create in any new project on first graph build.

Auto-Connect After Build

After building, the CLI automatically runs:

1. API connector — detects frontend HTTP calls matching backend route definitions
2. Implicit connector — detects behavioral relationships (entity events, bus messages, command events) based on rules in project-config.json → graphConnectors.implicitConnections[]

This creates edges for MESSAGE_BUS, TRIGGERS_EVENT, PRODUCES_EVENT, TRIGGERS_COMMAND_EVENT, and API_ENDPOINT — enabling full system flow tracing via the trace command.

Describe (AI-Friendly Command Reference)

Run python .claude/scripts/code_graph describe --json to get MCP-style structured descriptions of all available CLI commands, their parameters, and usage. Useful for AI agents to discover graph capabilities programmatically.

Valid CLI Subcommands

build, update, status, blast-radius, query, connections, trace, search, find-path, batch-query, sync, export, export-mermaid, connect-api, connect-implicit, review-context, describe

migrate-paths is also available to convert existing databases built with absolute file paths into repo-relative storage without reparsing the repository.

Common Mistakes (DO NOT USE)

Invalid Command	Correct Alternative
incremental	update --json (incremental is the default behavior of update)
update --files <list>	update --json (auto-detects changed files via git diff)
build --files <list>	build --json (always does full rebuild)
sync --files <list>	sync --json (auto-detects from git)
file_summary	connections <file> --json

---

Build Graph

Build or incrementally update the persistent code knowledge graph for this repository.

AI Mistake Prevention — Failure modes to avoid on every task:

Re-read files after context changes. Context compaction, resume, or long-running work can make memory stale; verify current files before acting. Verify generated content against source evidence. AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing. Check downstream references before deleting or renaming. Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first. Trace the full impact chain after edits. Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done. Verify ALL affected outputs, not just the first. One green check is not all green checks; validate every output surface the change can affect. Assume existing values are intentional — ask WHY before changing. Before changing a constant, limit, flag, wording, or pattern, read nearby context and history. Surface ambiguity before acting — don't pick silently. Multiple valid interpretations require an explicit question or stated assumption with risk. Keep shared guidance role-relevant. Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

MUST ATTENTION apply critical + sequential thinking — every claim needs appropriate traced evidence (file:line for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.

MUST ATTENTION apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting.

Closing Reminders

Protocols in force (concise digest of the SYNC/shared blocks this skill carries) — MUST ATTENTION honor each canonical body:

• AI Mistake Prevention: verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity.

• Critical Thinking: traced file:line proof per claim, confidence >80%, NEVER guess as fact.

• MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using task tracking BEFORE starting

• MANDATORY IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code

• MANDATORY IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act)

• MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify work quality

[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using task tracking.

Hookless Prompt Protocol Mirror (Auto-Synced)

Source: .claude/.ck.json + .claude/skills/shared/sync-inline-versions.md (:full blocks) + .claude/scripts/lib/hookless-prompt-protocol.cjs

[WORKFLOW-EXECUTION-PROTOCOL] [BLOCKING] Workflow Execution Protocol — MANDATORY IMPORTANT MUST CRITICAL. Do not skip for any reason.

Generic portability boundary: Reusable skills and protocol text stay project-neutral; project-specific conventions are discovered from docs/project-config.json and docs/project-reference/. Apply shared AI-SDD from shared/sdd-artifact-contract.md. Read docs/project-config.json and docs/project-reference/docs-index-reference.md, then open the project reference docs named there. For spec, test-case, behavior-change, public-contract, or docs/specs/ work, route through the local spec docs named by the docs index: feature-spec-reference.md, spec-system-reference.md, spec-principles.md, and workflow-spec-test-code-cycle-reference.md when specs/tests/code must stay synchronized. If either file or a required reference doc is missing or stale, auto-run $project-init (or the narrow lower-level route such as $project-config, $docs-init, $scan-all, or $scan --target=<key>) before ordinary project-specific work. Any supported AI tool may execute when this shared context and local docs are available.

1. DETECT: If the prompt starts with an explicit slash skill/workflow command, execute it directly. Otherwise match the prompt against the workflow catalog and skill list.
2. ANALYZE: Choose the best option: execute directly, invoke a skill, activate a standard workflow, or compose a custom step combination.
3. AUTO-SELECT: Pick the best option yourself. Do not ask the user to choose between direct execution, skill, standard workflow, or custom workflow.
4. ACTIVATE: For a selected workflow, call $start-workflow <workflowId>; for a selected skill, invoke that skill; for a custom workflow, sequence custom steps directly; for direct execution, proceed with the task.
5. CREATE TASKS: task tracking for ALL workflow/skill/custom steps before execution when the selected path has multiple steps.
6. EXECUTE: Advance per the Workflow Step Advancement & Parallel Phases rule in your context instructions — model-driven; a sub-agent completion advances a step identically to an inline call; a parallel-phase group is an all-return barrier (advance only after ALL members return, never serialize it)

Shared AI-SDD Protocol Markers

Source: .claude/skills/shared/sync-inline-versions.md

SYNC:ai-sdd-artifact-contract

AI-SDD Artifact Contract — Shared spec-driven development rules stay portable and source-owned.

1. Keep reusable AI-SDD principles in .claude; put repository-specific paths, commands, owners, products, and formats in project config/reference docs.
2. Preserve cycle: spec -> plan -> tasks -> implement -> verify -> update spec/docs.
3. Trace every requirement or invariant through decision, task, TC/test, source evidence, and docs/spec update.
4. Treat code-to-spec extraction as reference-only until accepted by the canonical spec owner.
5. Any supported AI tool may plan, implement, review, or verify with synced context; using multiple tools is optional.
6. Update .claude source first, then sync generated mirrors; do not manually edit .agents, .codex, or AGENTS.md. — why: mirrors are generated artifacts; hand-edits are overwritten on the next sync
7. If docs/project-config.json, root instruction files, or a required project-reference doc is missing or stale, auto-run $project-init or the narrow lower-level route before ordinary project-specific work.

Active reference: shared/sdd-artifact-contract.md in the active skills root.

---

SYNC:ai-sdd-artifact-contract:reminder

• MANDATORY Apply shared/sdd-artifact-contract.md; keep reusable AI-SDD in .claude and local rules in project docs.
• MANDATORY Code-to-spec extraction is reference-only until canonical acceptance; any supported AI tool may execute with synced context.
• MANDATORY Update .claude source before syncing generated mirrors; do not manually edit .agents, .codex, or AGENTS.md.
• MANDATORY Missing or stale project config, root instruction files, or required reference docs route project-specific work through $project-init or the narrow setup route automatically. [TASK-PLANNING] [MANDATORY] BEFORE executing any workflow or skill step, create/update task tracking for all planned steps, then keep it synchronized as each step starts/completes.

[LESSON-LEARNED-REMINDER] [BLOCKING] Task Planning & Continuous Improvement — MANDATORY. Do not skip.

Break work into small tasks (task tracking) before starting. Add final task: "Analyze AI mistakes & lessons learned".

Extract lessons — ROOT CAUSE ONLY, not symptom fixes:

1. Name the FAILURE MODE (reasoning/assumption failure), not symptom — "assumed API existed without reading source" not "used wrong enum value".
2. Generality test: does this failure mode apply to ≥3 contexts/codebases? If not, abstract one level up.
3. Write as a universal rule — strip project-specific names/paths/classes. Useful on any codebase.
4. Consolidate: multiple mistakes sharing one failure mode → ONE lesson.
5. Recurrence gate: "Would this recur in future session WITHOUT this reminder?" — No → skip $learn.
6. Auto-fix gate: "Could $code-review/$code-simplifier/$security-review/$lint catch this?" — Yes → improve review skill instead.
7. BOTH gates pass → ask user to run $learn. [CRITICAL-THINKING-MINDSET] Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination principle: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination. AI Attention principle (Primacy-Recency): Put the 3 most critical rules at both top and bottom of long prompts/protocols so instruction adherence survives long context windows. Goal-driven execution: Define success criteria first, loop until verified, and stop only when observable checks pass. Tests verify intent: Tests must protect business rules/invariants and fail when the protected intent breaks, not only mirror current behavior.

Common AI Mistake Prevention (System Lessons)

• Re-read files after context compaction. Edit requires prior Read in same context; compaction wipes read state. Re-read before editing.
• Grep for old terms after bulk replacements. AI over-trusts find/replace completeness. Grep full repo after bulk edits for missed refs in docs/configs/catalogs.
• Check downstream references before deleting. Deletions cascade doc/code staleness. Map referencing files before removal.
• After memory loss, check existing state before creating new. Compaction wipes prior-work memory. Query current state to resume — never blindly duplicate.
• Verify AI-generated content against actual code. AI hallucinates APIs, class names, method signatures. Grep to confirm existence before documenting/referencing.
• Trace full dependency chain after edits. Changing a definition misses downstream consumers. Trace the full chain.
• When renaming, grep ALL consumer file types. Some file types silently ignore missing refs (no compile error). Search code, templates, configs, generated files.
• Trace ALL code paths when verifying correctness. Code existing ≠ code executing. Trace early exits, error branches, conditional skips — not just happy path.
• Update docs that embed canonical data when source changes. Docs inlining derived data (workflows, schemas, configs) go stale silently. Update all embedding docs alongside source.
• Verify sub-agent results after context recovery. Background agents may finish while parent compacted — grep-verify output, don't trust assumed completion.
• Cross-check full target list against sub-agent assignments. Parallel sub-agents by category miss boundary items. Reconcile union of assignments against target list before proceeding.
• Sub-agents inherit knowledge only from their agent .md definition — use custom agent types, not built-in Explore. Tool adoption = permission + knowledge + enforcement (numbered workflow step).
• Persist sub-agent findings incrementally, not as a final batch. Long sub-agents hit cutoffs before final write — findings lost. Instruct append-per-section to report file.
• When debugging, ask "whose responsibility?" before fixing. Trace caller (wrong data) vs callee (wrong handling). Fix at responsible layer — never patch symptom site.
• Grep ALL removed names after extraction/refactoring. Primary file "done" ≠ secondary files clean. Grep entire scope for every removed symbol before declaring complete.
• Assume existing values are intentional — ask WHY before changing. Pattern-matching as "wrong" skips context. Before changing any constant/limit/flag: read comments, git blame, surrounding code.