
Document Service
Activate this when you inherit an undocumented codebase and need to understand what it actually does. It generates structured technical documentation with source-of-truth citations, tracing every claim back to specific files and line numbers. The workflow is autonomous after you point it at a directory. It maps architecture, traces request flows end to end, deep dives complex logic, and surfaces implicit knowledge like hardcoded values and unhandled failure modes. Optimized for AWS workloads with CDK, CloudFormation, and Terraform parsing, but works on any codebase. Think of it as the "it's 3am and this is broken, where do I look" analysis your team never had time to write.
- GitHub stars
- 783
- last updated
- Jun 11, 2026
Install
$ npx -y skills add awslabs/agent-plugins --skill document-service --agent claude-codeInstalls into .claude/skills of the current project.
Files
Document Service
Analyze codebases to produce structured technical documentation and architecture diagrams with source-of-truth citations. Every finding links back to the exact file and line it was derived from. Optimized for AWS workloads but works with any codebase.
Core Principles
Sponsors
Details
- Repository
- github.com/awslabs/agent-plugins
- Category
- AI & Agent Building
- License
- Apache-2.0
- First seen
- Jun 11, 2026
More from awslabs/agent-plugins
All 32- Dsql
- Elastic Beanstalk
- Finetuning Technique
- Hyperpod Cluster Debugger
- Hyperpod Nccl
- Hyperpod Node Debugger
- Hyperpod Performance Debugger
- Hyperpod Slurm Debugger
- Model Selection
- Sdk Getting Started
- Aws Architecture Diagram358
- Aws Lambda260
- Deploy240
- Directory Management183
- Use Case Specification183
- Planning168
- Dataset Evaluation156
- Aws Serverless Deployment154
- Finetuning154
- Model Deployment154
- Dataset Transformation153
- Hyperpod Ssm150
- Hyperpod Version Checker149
- Hyperpod Issue Report147