Plan Synthesizer — Data & AI agent for Claude Code
Perform deep semantic analysis on collected project data to identify drift, gaps, and create a prioritized reconstruction plan.
How to install Plan Synthesizer
Installs to ~/.claude/agents/agent-sh-drift-detect-plan-synthesizer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/agent-sh/drift-detect/HEAD/agents/plan-synthesizer.md -o ~/.claude/agents/agent-sh-drift-detect-plan-synthesizer.md Restart Claude Code, or start a new session, for it to be picked up.
What Plan Synthesizer does
name: plan-synthesizer description: Perform deep semantic analysis on collected project data to identify drift, gaps, and create a prioritized reconstruction plan. Use this agent for the single LLM analysis call after JavaScript data collection. tools:
- Read
- Write model: sonnet
Plan Synthesizer Agent
You perform deep semantic analysis on project data collected by the JavaScript collectors module. Your role is to identify patterns, drift, and gaps that require human-level reaso
Alternatives in Data & AI
- Docs Drift Reviewer — Checks whether clickhouse-go documentation matches changes to its ClickHouse API, database/sql API, transports 3.3k ★
- Cross Service Auditor — Phase 8 cross-service taint-propagation agent that stitches inter-component data flows (HTTP/gRPC/queues/IPC/s 125 ★
- Design Guardian — Accountable design decider and applier 79 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
PR Code Analyzer
Stage 2 of the PR review pipeline. Deep code analysis over data already collected by pr-data-collector — appli
Newsletter Competitive Analyst
Use this agent when you need to analyze competing AI newsletters to identify content gaps, differentiation opp
Repo Retrospective
Quality assurance agent for AI onboarding documentation. Analyzes ONBOARD documents against X-Ray outputs and
Priority Scorer
Scores and ranks AI mapping opportunities by revenue impact, capital reduction, and implementation ease. Produ
Data Model Auditor
Use when analysis-orchestrator audits a codebase for schema/mapping/migration drift and referential integrity
Glm Agent
Runs Z.AI GLM on the user's GLM Coding Plan. Three modes - consult (direct API call, 1M context, for inputs to
Related Skills
Audit Deep
Full-stack audit: architecture, code quality, performance, UX debt, security, test gaps. Produces prioritized
Docguard.Review
Review documentation quality — identify drift, coverage gaps, and improvements
J Diff Review
Deep multi-perspective diff review — code quality, security, testing gaps, documentation drift, observability