Use when analyzing existing codebases to generate architecture documentation - coordinates subagent-driven exploration with mandatory workspace structure, validation gates, and pressure-resistant workflows
View on GitHubtachyon-beep/skillpacks
axiom-system-archaeologist
plugins/axiom-system-archaeologist/skills/using-system-archaeologist/SKILL.md
January 24, 2026
Select agents to install to:
npx add-skill https://github.com/tachyon-beep/skillpacks/blob/main/plugins/axiom-system-archaeologist/skills/using-system-archaeologist/SKILL.md -a claude-code --skill using-system-archaeologistInstallation paths:
.claude/skills/using-system-archaeologist/# System Archaeologist - Codebase Architecture Analysis ## Overview Analyze existing codebases through coordinated subagent exploration to produce comprehensive architecture documentation with C4 diagrams, subsystem catalogs, and architectural assessments. **Core principle:** Systematic archaeological process with quality gates prevents rushed, incomplete analysis. --- ## Context Conservation (CRITICAL) **You are a COORDINATOR, not an analyst.** Your primary context is precious - preserve it for orchestration decisions, not detailed code reading. ### The Delegation Imperative | Task Type | Your Role | Subagent Role | |-----------|-----------|---------------| | Subsystem analysis | Spawn `codebase-explorer` | Read files, produce catalog entries | | Validation | Spawn `analysis-validator` | Check contracts, produce reports | | Diagram generation | Spawn diagram subagent | Generate Mermaid/PlantUML | | Quality assessment | Spawn quality subagent | Analyze patterns, produce assessment | | Security surface | Spawn security subagent | Map boundaries, flag concerns | ### What You DO (Coordinator): - Create workspace and coordination plan - Make orchestration decisions (parallel vs sequential) - Spawn subagents with clear task specifications - Read subagent outputs (summaries, not raw files) - Make proceed/revise decisions based on validation - Synthesize final deliverables from subagent work ### What You DO NOT Do (Delegate Instead): - Read implementation files directly (subagent reads, you get summary) - Perform detailed pattern analysis (spawn specialist) - Write catalog entries yourself (spawn codebase-explorer) - Validate your own work (spawn analysis-validator) - Generate diagrams from scratch (spawn diagram agent) ### Rationalization Blockers | Thought | Reality | |---------|---------| | "I'll just quickly read this file" | Spawn subagent. Your context is for coordination. | | "It's faster if I do it myself" | Subagents preserve your context for later dec