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 EvidInvest/aether-developer --skill aether-researchgit clone --depth 1 https://github.com/EvidInvest/aether-developerWrote 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/evidinvest/aether-developer/aether-research)<a href="https://agentmods.dev/skills/evidinvest/aether-developer/aether-research"><img src="https://agentmods.dev/badge/skills/evidinvest/aether-developer/aether-research/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/evidinvest/aether-developer/aether-research"><img src="https://agentmods.dev/badge/skills/evidinvest/aether-developer/aether-research.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 | $0.00068 | $0.02460 |
| Opus 5.5 | $0.00027 | $0.00984 |
| Sonnet 5.5 | $0.00014 | $0.00492 |
| Haiku 4.5 | $0.00007 | $0.00246 |
Grade A, and why
aether-research 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.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aether equity research
You have access to Aether — a search engine built for agents over SEC filings, earnings-call transcripts, and EU financial regulation. Every hit returns the exact primary-source passage, an accession-numbered citation, and a sec.gov / EUR-Lex URL. Your job: use it so every factual claim in your answer traces to a filed document.
Rule one: name the company, then narrow
Every company tool takes an issuer — {ticker}, {cik}, or
{company_name} for non-US filers with no US ticker. Put the company in
issuer and the question in query:
{"query": "data center revenue growth drivers", "issuer": {"ticker": "NVDA"}, "fiscal_year": 2027}
Not {"query": "NVDA data center revenue growth drivers"}. Both appear to
work, which is what makes the second one dangerous: with no issuer the
engine guesses the filer from your query text, and generic words that happen
to be tickers point it at the wrong company. Measured: the ordinary word
"customers" resolves to Customers Bancorp, which then took two ranks of an
NVIDIA memo.
Then read two fields off every response before you use it:
scope—"issuer"or"cross_company".quality_caveat— present when the answer is not issuer-precise.
scope: "issuer" with no caveat is the only guarantee you got a filtered
answer. A caveat arriving with scope: "issuer" means the engine guessed the
company and names its guess — check it is the one you meant. A
cross_company answer spans every filer and is ranked by relevance only: say
so in your write-up rather than presenting it as a complete list.
Use scope: "cross_company" deliberately, for questions genuinely about many
issuers ("which filers name NVIDIA as a supplier"), and budget up to 15 s for
it. Then re-run scoped on any company worth a closer look.
Rule two: if you know the document, don't rank it
query is optional. Omit it and you get fetch mode: pass an identifier
(issuer.ticker / issuer.cik / issuer.company_name / accession_number)
plus any of form_type / fiscal_year / section / quarter, and the filing
comes back in filing order — newest first, then document order, so Item 1
precedes Item 1A precedes Item 2. No ranking, tens of milliseconds,
mode: "fetch", and no confidence field because nothing was scored.
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 Changed · +90 lines · +8 tokens per session 05a0eccd1adf
- 1mo ago First seen · 80 lines · 60 tokens per session scan A cc6e99244f8c
aether-research is a skill published in the GitHub repository EvidInvest/aether-developer (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 68 tokens to every session and 2,460 once invoked, about $0.0003 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
EdgarTools
Query and analyze SEC filings using EdgarTools.
tickdb-market-data
A real-time market-data API for foreign exchange, metals, indexes, stocks, and cryptocurrencies. An API is a service that software can call to request data.
defeatbeta-earnings-analysis
Create professional equity research earnings update reports (8-12 pages, 3,000-5,000 words) analyzing quarterly results for companies already under coverage. Fast-turnaround format focusing on beat/miss analysis, key metrics, updated estimates, and revised thesis. Includes 1-3 summary tables and 8-12 charts. Use when…
defeatbeta-earnings-preview
Build pre-earnings analysis with normalized baselines, weighted decision models, company-specific veto gates, scenario frameworks, catalysts, historical reactions, and options-implied moves. Use before a company reports quarterly earnings to prepare positioning notes or bilingual three-page PDF reports.
defeatbeta-earnings-key-data
Run one of three traceable earnings-call transcript templates through the DefeatBeta MCP tools: (1) extract current-quarter results plus next-quarter and full-year guidance, (2) extract factual QoQ or YoY financial-metric change sentences, or (3) extract numerical forward-looking forecast sentences with…
sprr
Single PR reviewer for awesome-quant. Use when the user asks to review, validate, comment on, label, close, or merge one specific pull request that adds README.md entries. Triggers include "sprr", "review PR", "check PR", and "validate contribution".