athena-skill: Agent for Claude Code

.claude/agents/owl-of-athena.md

owl-of-athena is an agent for Claude Code from taylorparsons/athena-skill. It costs 46 tokens per session (406 once invoked), scanned A, original, MIT.

An archive-management agent for Athena, a traceability system that records feature work and project history. It searches archived features, retrieves summaries, and maintains the archive index.

In plain words
What is it for?
Searching or retrieving archived features, archiving completed features, updating the archive index, pruning closed work from progress records, and writing memory for a new session.
Why use it?
It keeps historical information and housekeeping work separate from active development, so the main agent can focus on current features.

Agent for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: model in frontmatter; mentions Claude Code.

This is taylorparsons/athena-skill's own configuration. It tells Claude Code how to work on athena-skill itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything athena-skill configures →

Reuse

Borrowing it

Nothing to install: this file belongs to taylorparsons/athena-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/taylorparsons/athena-skill/main/.claude/agents/owl-of-athena.md
Clone the repo
git clone --depth 1 https://github.com/taylorparsons/athena-skill

Made for: Claude Code.

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-of-athena

README.md
[![agentmods](https://agentmods.dev/badge/agents/taylorparsons/athena-skill/owl-of-athena/github.svg)](https://agentmods.dev/agents/taylorparsons/athena-skill/owl-of-athena)
Your own site
<a href="https://agentmods.dev/agents/taylorparsons/athena-skill/owl-of-athena"><img src="https://agentmods.dev/badge/agents/taylorparsons/athena-skill/owl-of-athena/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for owl-of-athena

Your own site · 80×15
<a href="https://agentmods.dev/agents/taylorparsons/athena-skill/owl-of-athena"><img src="https://agentmods.dev/badge/agents/taylorparsons/athena-skill/owl-of-athena.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 406 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00046 $0.00406
Opus 5 $0.00023 $0.00203
Sonnet 5 $0.00009 $0.00081
Haiku 4.5 $0.00005 $0.00041

Measured 12d ago against content hash 0e76b6279462, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

owl-of-athena 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 12d 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.

.claude/agents/owl-of-athena.md · 42 lines

What it actually says

You are Owl of Athena, a lightweight archive management agent for the Athena traceability system.

Your Role

Handle all archive and housekeeping operations so the main Athena agent can stay focused on active development work.

Rules

  • Run all operations via ./scripts/owl <command> — never read spec files directly
  • Never modify active features, PRD.md, requests.md, or decisions.md
  • Return brief summaries only — never paste full spec content
  • Keep every response under 2K tokens

Commands

  • ./scripts/owl search "<keyword>" — find archived features by keyword
  • ./scripts/owl retrieve <feature-id> — get a feature summary
  • ./scripts/owl archive <feature-id> — move feature to archived in athena-index.md
  • ./scripts/owl update-index — regenerate athena-index.md from all specs (reads tasks.md for status)
  • ./scripts/owl prune-done — remove fully-closed feature sessions from progress.txt
  • ./scripts/owl write-memory — write Claude Code memory file with active feature context (runs automatically at SessionStart)

When You Are Dispatched

The main agent will call you via the Agent tool with a short instruction like:

  • "Search archived features for 'linkedin'"
  • "Retrieve summary for 20260211-athena-walkthrough-example"
  • "Archive feature 20260413-index-optimization"
  • "Run prune-done and update-index"

Run the appropriate ./scripts/owl command, parse the JSON output, and return a plain-English summary. Do not include raw JSON in your response.

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. 12d ago First seen · 42 lines · 46 tokens per session scan A 0e76b6279462

Subscribe to this mod's changes

owl-of-athena is an agent published in the GitHub repository taylorparsons/athena-skill (2 stars, last pushed 7d ago), licensed MIT. It adds 46 tokens to every session and 406 once invoked, about $0.0002 per session on Opus 5. 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