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.
npx skills add taylorparsons/athena-skill --skill codexgit clone --depth 1 https://github.com/taylorparsons/athena-skillWrote 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.
[](https://agentmods.dev/skills/taylorparsons/athena-skill/codex)<a href="https://agentmods.dev/skills/taylorparsons/athena-skill/codex"><img src="https://agentmods.dev/badge/skills/taylorparsons/athena-skill/codex/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.
<a href="https://agentmods.dev/skills/taylorparsons/athena-skill/codex"><img src="https://agentmods.dev/badge/skills/taylorparsons/athena-skill/codex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.00359 |
| Opus 5.5 | $0.00020 | $0.00144 |
| Sonnet 5.5 | $0.00010 | $0.00072 |
| Haiku 4.5 | $0.00005 | $0.00036 |
Grade A, and why
athena-codex 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 1mo 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.
What it actually says
ATHENA Codex Adapter
The loop is identical on every harness — follow ../../skills/athena/SKILL.md. This adapter only covers Codex wiring.
Codex wiring
-
Session open: run
./scripts/owl context(Codex has no hooks or auto-memory — the script is the mechanism). -
Keep
~/.codex/AGENTS.mdminimal (trigger + stop-gates only, ≤ 15 lines). Do not duplicate loop steps there — the loop lives in SKILL.md. Recommended block:## ATHENA — mandatory for all coding work - Invoke the athena skill before any change and follow its loop exactly. - Session open: ./scripts/owl context - Never Read docs/requests.md, docs/decisions.md, or docs/athena-index.md — use ./scripts/owl (add-request, add-decision, add-note, show, why). - No code changes until the current request is captured (owl add-request) and reflected in docs/PRD.md. - If any gate above was skipped, STOP and restart with ATHENA. -
Install the full package with
$skill-installerinto$CODEX_HOME/skills/athena, then run scripts from$CODEX_HOME/skills/athena/scripts/(or a local./scripts/owlwrapper).
Versioning
Use Semantic Versioning from ../../VERSION. Breaking process changes require a major bump.
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.
- 1mo ago First seen · 29 lines · 50 tokens per session scan A c58119cb8d08
athena-codex is a skill published in the GitHub repository taylorparsons/athena-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 359 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
aip-tracker
Track Airflow Improvement Proposal (AIP) implementation progress by comparing Confluence specs against codebase evidence. Use when asked to assess, report on, or compare AIP status.
mempalace-task
Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.
intake
Inspect configured Sources and propose evidence-backed Backlog work.
refresh
Refresh Product status from current work and source evidence.
summary
Deliver the Product summary through its configured interface and wiki.
gh
GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, (6) Install and manage…