Borrowing it
Nothing to install: this file belongs to omacom/aether. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/omacom/aether/main/.claude/skills/aether-docs/SKILL.mdgit clone --depth 1 https://github.com/omacom/aetherWrote 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/omacom/aether/aether-docs)<a href="https://agentmods.dev/skills/omacom/aether/aether-docs"><img src="https://agentmods.dev/badge/skills/omacom/aether/aether-docs/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/omacom/aether/aether-docs"><img src="https://agentmods.dev/badge/skills/omacom/aether/aether-docs.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 | $0.00104 | $0.00543 |
| Opus 5.5 | $0.00042 | $0.00217 |
| Sonnet 5.5 | $0.00021 | $0.00109 |
| Haiku 4.5 | $0.00010 | $0.00054 |
Grade A, and why
aether-docs 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 2mo 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
Aether detailed documentation
The in-repo docs (README.md, docs/*.md, CLAUDE.md) cover only the minimum needed to build, run, and understand the public feature surface. Detailed project documentation lives outside the repo at:
~/Documents/bjarne/projects/Aether
When to consult this folder
- Before implementing a non-trivial feature — check for existing design docs, prior decisions, or half-finished drafts on the area you're touching.
- Before architectural changes — look for ADRs or flow diagrams that explain why things are structured as they are.
- When the user asks "how does X work" or "why did we build X that way" and the answer isn't obvious from code.
- After a significant design discussion — write a new doc so future work has the context.
How to use
ls ~/Documents/bjarne/projects/Aether
rg "<topic>" ~/Documents/bjarne/projects/Aether
Read relevant files before drafting a plan. Cite the filename when you rely on one.
Writing new docs
When the user asks you to document a design decision, flow, or feature internal:
- Write to
~/Documents/bjarne/projects/Aether/<topic>.md. - Use a short descriptive filename (e.g.
palette-extraction-pipeline.md,eyedropper-loupe-design.md,adr-001-split-sidebars.md). - Include date headers so the reader can see when something was decided.
Do not put these detailed docs into the repo's docs/ folder — that directory is reserved for user-facing documentation (CLI usage, installation, custom apps, custom templates, wallhaven setup, etc.).
Do not
- Don't guess at Aether's architecture or history without checking this folder first — the user keeps decisions here rather than in commit messages or PR descriptions.
- Don't duplicate content from here into the repo.
- Don't commit anything to git from this folder — it's deliberately outside version control.
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.
- 2mo ago First seen · 52 lines · 104 tokens per session scan A b7d58be2af93
aether-docs is a skill published in the GitHub repository omacom/aether (776 stars, last pushed 5d ago), licensed MIT. It adds 104 tokens to every session and 543 once invoked, about $0.0004 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 2026-08-30.
aether-docs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aether-docsomacom/aether | Skill | 776 | 5d ago | MIT | A | 104 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |