TP / Open source

Agent workflows / Skill + CLI

ATHENA

Keep an audit trail from a request to shipped code.

View source ↗Try it ↓
  1. 01Request + decision
  2. 02Spec + task
  3. 03Code + evidence

When to use it

Use an AI coding agent on a project that needs recorded decisions, requirements, tasks, and execution evidence.

Get started

Requirements

Codex or Claude Code, Python 3, Git.

Terminal
git clone https://github.com/taylorparsons/athena-skill.git
cd athena-skill
cp -r skills/athena ~/.claude/skills/

How to use

  1. Install the packaged skills/athena directory in your agent skill directory. Codex installation is documented in the source README.
  2. Restart the agent and ask it to set up ATHENA docs in your project.
  3. Open sessions with ./scripts/owl context. Capture requests, specify a feature, execute tasks, and record evidence through Owl.
  4. Use ./scripts/owl show <ID> or ./scripts/owl why <FR-ID> to inspect a decision or requirement chain.

Under the hood

Owl is the deterministic gateway for context and audit records. The optional Owl agent and hooks are documented for Claude Code. Codex uses the CLI.

ATHENA repository visual
Visual from the public repository.

Open source recognition

Meet the maintainers and contributors, view dependency sources, and read original license notices ↗

Source documentation

Setup instructions are taken from the public repository. Dependencies, API availability, and scripts can change; check the source README for updates.

Questions or issues ↗

Explore another workflow

Browse by use case ↗