agentlensNavigate and understand codebases using agentlens hierarchical documentation. Use when exploring new projects, finding modules, locating symbols in large files, finding TODOs/warnings, or understanding code structure.
Install via ClawdBot CLI:
clawdbot install nguyenphutrong/agentlensAlways start by reading .agentlens/INDEX.md for the project map.
| Level | File | Purpose |
|-------|------|---------|
| L0 | INDEX.md | Project overview, all modules listed |
| L1 | modules/{slug}/MODULE.md | Module details, file list |
| L1 | modules/{slug}/outline.md | Symbols in large files |
| L1 | modules/{slug}/memory.md | TODOs, warnings, business rules |
| L1 | modules/{slug}/imports.md | File dependencies |
| L2 | files/{slug}.md | Deep docs for complex files |
INDEX.md ā Find module ā MODULE.md ā outline.md/memory.md ā Source file
| You Need | Read This |
|----------|-----------|
| Project overview | .agentlens/INDEX.md |
| Find a module | INDEX.md, search module name |
| Understand a module | modules/{slug}/MODULE.md |
| Find function/class in large file | modules/{slug}/outline.md |
| Find TODOs, warnings, rules | modules/{slug}/memory.md |
| Understand file dependencies | modules/{slug}/imports.md |
agentlens command if they seem staleFor detailed navigation patterns, see references/navigation.md
For structure explanation, see references/structure.md
Generated Mar 1, 2026
A new developer joins a team maintaining a large, undocumented legacy system. They use AgentLens to quickly understand the project structure via INDEX.md, locate relevant modules, and identify critical sections in files using outline.md and memory.md, reducing ramp-up time from weeks to days.
A senior engineer needs to refactor a complex module for performance improvements. They consult memory.md to check for existing TODOs and warnings, use outline.md to navigate large files efficiently, and verify dependencies with imports.md to ensure changes don't break other parts of the system.
A contributor wants to add a feature to an open-source project. They start with INDEX.md to grasp the overall architecture, find the target module via MODULE.md, and use outline.md to locate specific functions to modify, avoiding unnecessary deep dives into unrelated source code.
A security analyst audits a codebase for vulnerabilities. They rely on memory.md to spot documented warnings and TODOs related to security issues, use outline.md to quickly scan large files for risky symbols, and cross-reference imports.md to understand dependency chains that might introduce risks.
Offer AgentLens as a free open-source tool for basic codebase navigation, with premium features like advanced analytics, team collaboration dashboards, and integration with CI/CD pipelines. Revenue is generated through subscription plans for enterprises and large teams.
Provide consulting services to help organizations implement AgentLens in their development workflows, along with training workshops for teams. Revenue comes from project-based fees and ongoing support contracts for customization and maintenance.
Host AgentLens as a cloud-based SaaS platform where teams can upload and analyze codebases securely. Offer features like real-time documentation updates, collaboration tools, and API access. Revenue is generated through monthly or annual subscriptions based on usage and team size.
š¬ Integration Tip
Integrate AgentLens into your existing development workflow by adding it as a pre-commit hook to automatically regenerate docs, ensuring documentation stays up-to-date with code changes.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection