Autonomous technical-documentation generator. Scans a codebase, extracts symbols, structures a doc skeleton, drafts sections, verifies consistency, and publishes Markdown — offline by default, smarter with a BYO-LLM CLI.

Overview

This pack provides an operational autonomous agent for generating and maintaining the technical documentation of a software project.

It includes an OODA loop dedicated to the docgen domain, versioned prompts, configuration templates and a set of installation, test and execution scripts.

The pack is designed to be self-hosted (BYO-LLM): no API key is included, no third-party dependency (Python stdlib only). The LLM adapter automatically detects your own CLI (claude-code, kimi, codex; override via PACK_LLM) and calls it as a subprocess. Without an LLM, the agent runs in deterministic mode and produces a basic documentation structure.

Target audience

Teams that want up-to-date technical documentation without manual effort.
Solo developers who want a README/API doc generated on every commit.
LLM operators who want an autonomous, auditable documentation pipeline.

Architecture

┌─────────────────────────────────────────────────────────────────────┐
│                    Source code / repo / files                        │
└──────────────────────────────────┬──────────────────────────────────┘
                                   ▼
┌─────────────────────────────────────────────────────────────────────┐
│  IDLE → DISCOVER → EXTRACT → STRUCTURE → DRAFT → VERIFY → PUBLISH   │
│                        OODA State Machine                            │
└──────────────────────────────────┬──────────────────────────────────┘
                                   ▼
┌─────────────────────────────────────────────────────────────────────┐
│  Named prompts → Deterministic handler →  BYO-LLM Adapter           │
│  scripts/test_prompt.py    scripts/run_agent.py                     │
└──────────────────────────────────┬──────────────────────────────────┘
                                   ▼
┌─────────────────────────────────────────────────────────────────────┐
│  SQLite queue  →  templates/*.yaml  →  docs/output/*.md              │
└─────────────────────────────────────────────────────────────────────┘

Pack contents

File	Role
`README.md`	This file — overview and quick-start
`SOUL.md`	Mission, values and `docgen`-specific OODA states
`PROMPTS.md`	6 named, versioned system prompts
`CHECKLIST.md`	30+ operational steps with commands
`SPEC.md`	Technical spec, configurable parameters, interfaces
`CUSTOMIZE.md`	5-min guide: where to plug in your own sources/rules
`OPERATING_COST_ESTIMATE.md`	Provider-agnostic LLM cost estimate
`CHANGELOG.md`	Version history
`agent-docgen-v1.json`	Pack manifest with stats and files
`agent.py`	Runnable agent — SQLite queue, retry, dead-letter, OODA
`llm_adapter.py`	BYO-LLM adapter (claude/kimi/codex) without an API key
`install.sh`	One-shot Debian installer: deps + venv + systemd service
`agent-docgen-v1.service`	Reference systemd unit
`scripts/install.sh`	Automated installation script (copy + systemd)
`scripts/config.yaml`	Default runtime configuration
`scripts/test_prompt.py`	Named-prompt tester
`scripts/run_agent.py`	Convenience runner that delegates to agent.py via the venv
`templates/source_schema.yaml`	Source codebase schema template
`templates/doc_outline.yaml`	Documentation outline template
`templates/verification_policy.yaml`	Verification policy template

Quick installation

cd /opt/agents/agent-docgen-v1
bash install.sh

The installer checks for Python 3.10+, creates a venv, installs the dependencies, detects a local LLM provider and configures a systemd unit.

Immediate test

# Test the main prompt
python3 scripts/test_prompt.py --prompt codebase_scanner --input templates/source_schema.yaml

# Run the agent in dry-run mode
python3 scripts/run_agent.py --config scripts/config.yaml --dry-run

# Offline test suite
bash smoke_test.sh

Customization

Copy scripts/config.yaml to config.local.yaml.
Adapt the templates in templates/.
Plug your own code sources into run_agent.py or via agent.py enqueue.

See CUSTOMIZE.md for details.

Costs and limits

This pack favors deterministic logic for critical decisions. The LLM is used for semantic extraction, drafting and verification. See OPERATING_COST_ESTIMATE.md for the operating cost estimate.

License

Personal use per purchase. Resale prohibited.

Agent DocGen Pack v1.0

What's inside