OWL-IMPLEMENTATION

OWL-IMPLEMENTATION is an agent for coding agents from taylorparsons/athena-skill. It costs 0 tokens per session (1,852 once invoked), scanned A, original, MIT.

A command-line tool for managing completed development features in the Owl of Athena project. It uses project files such as task lists, specifications, and product requirements documents.

In plain words
What is it for?
Removing closed feature sessions, rebuilding a feature index, searching archived work, retrieving feature summaries, and archiving finished features.
Why use it?
It keeps progress records and archived feature information tidy as work is completed.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/taylorparsons/athena-skill/owl-implementation
Clone the repo
git clone --depth 1 https://github.com/taylorparsons/athena-skill

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for OWL-IMPLEMENTATION

README.md
[![agentmods](https://agentmods.dev/badge/agents/taylorparsons/athena-skill/owl-implementation.svg)](https://agentmods.dev/agents/taylorparsons/athena-skill/owl-implementation)
Your own site
<a href="https://agentmods.dev/agents/taylorparsons/athena-skill/owl-implementation"><img src="https://agentmods.dev/badge/agents/taylorparsons/athena-skill/owl-implementation.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,852 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01852
Opus 5 $0.00000 $0.00926
Sonnet 5 $0.00000 $0.00370
Haiku 4.5 $0.00000 $0.00185

Measured 4d ago against content hash c3a7ae77e56d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

OWL-IMPLEMENTATION scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/OWL-IMPLEMENTATION.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Owl of Athena: Implementation

Status: ✅ Implemented
Script: scripts/owl.py
Wrapper: scripts/owl

Quick Start

# Remove closed feature sessions from progress.txt
./scripts/owl prune-done

# Update athena-index.md from current specs (reads tasks.md for status)
./scripts/owl update-index

# Search archived features
./scripts/owl search "linkedin"

# Retrieve feature summary
./scripts/owl retrieve 20260211-athena-walkthrough-example

# Archive a feature (mark as Done in INDEX)
./scripts/owl archive 20260413-my-feature

Commands

prune-done

Remove session blocks for fully-closed features from progress.txt.

A feature is fully closed when ALL three are true:

  1. tasks.md — no items under NEXT or IN PROGRESS
  2. spec.mdStatus: Done
  3. PRD.md — feature appears as shipped/complete

Usage: ./scripts/owl prune-done

Output:

{
  "success": true,
  "pruned_features": ["20260213-linkedin-post-variants"],
  "blocks_removed": 3,
  "message": "✅ Pruned 3 session block(s) for 1 closed feature(s)"
}

When it runs: Automatically via the Claude Code Stop hook at session end. Can also be run manually.

update-index

Regenerate athena-index.md from all specs in docs/specs/. Reads tasks.md first to determine Active vs Done status — falls back to spec.md Status field if no tasks.md exists.

Usage: ./scripts/owl update-index

Output:

{
  "success": true,
  "total_features": 19,
  "active": 0,
  "archived": 19,
  "message": "✅ Updated athena-index.md: 0 active, 19 archived"
}

write-memory

Write a Claude Code auto-memory file (project_athena_active.md) to ~/.claude/projects/<encoded-repo>/memory/ containing the active feature, goal, and task state from progress.txt and active features from athena-index.md. Athena reads this at session start and skips re-reading those two files.

Usage: ./scripts/owl write-memory

Output:

{
  "success": true,
  "memory_file": "/Users/.../.claude/projects/-Volumes-T9-code-SKILLS-athena/memory/project_athena_active.md",
  "feature_id": "20260414-owl-memory-bridge",
  "active_features": 1,
  "message": "✅ Wrote memory: 20260414-owl-memory-bridge, 1 active feature(s)"
}

Read the full file on GitHub · 246 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 246 lines · 0 tokens per session scan A c3a7ae77e56d

Subscribe to this mod's changes

OWL-IMPLEMENTATION is an agent published in the GitHub repository taylorparsons/athena-skill (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,852 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories