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 OneWave-AI/open-agent-stack --skill earnings-watchgit clone --depth 1 https://github.com/OneWave-AI/open-agent-stackWrote 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/onewave-ai/open-agent-stack/earnings-watch)<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/earnings-watch"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/earnings-watch.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.00457 |
| Opus 5 | $0.00026 | $0.00229 |
| Sonnet 5 | $0.00010 | $0.00091 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
earnings-watch 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 7d 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
Earnings Watch
Earnings season punishes the unprepared with surprises and rewards the prepared with context. This skill builds the calendar and the per-name prep sheet -- what to watch, not what will happen. No forecasts, no trade suggestions.
Workflow
- Build the calendar. For each holding/watchlist ticker: confirmed or expected report date and time (web-verified; expected dates marked as unconfirmed), sorted chronologically. Flag clusters -- three holdings reporting the same week deserves knowing in advance.
- Per-name prep sheet. For each upcoming report: what the company guided last quarter (the promise being graded), the 2-3 line items coverage says matter this time (a margin number, a subscriber count, a segment's growth), any pre-announcements or peer results that set expectations, and how the stock has behaved into recent prints (context, not prediction).
- The holder's questions. Per name, what this report could clarify about the owner's original thesis: "You hold this for the cloud segment -- watch whether its growth re-accelerated." Tie the watching back to the reason for owning.
- Post-report debrief (on request, after a print): what was reported vs. guided, what management said about the items flagged, and whether anything changed the facts of the holding thesis -- laid out for the owner to judge, not judged for them.
Rules
- No predictions -- not of results, not of stock reactions. The prep sheet says what to watch, never what will happen.
- Dates get verified and labeled confirmed/expected; a wrong earnings date is the most embarrassing possible error here.
- Expectations context comes from cited coverage, marked as narrative, not fact.
- The debrief reports; the owner concludes. Anything resembling "this changes the thesis, consider selling" is out of scope and says so.
- Sources and dates on everything; earnings-adjacent web data goes stale in hours.
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.
- 7d ago First seen · 24 lines · 52 tokens per session scan A 117f2f9f0d6b
earnings-watch is a skill published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 27d ago), licensed MIT. It adds 52 tokens to every session and 457 once invoked, about $0.0003 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.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
lbo-model
Build leveraged buyout workbooks with IRR/MOIC in Excel.
excel-author
Build auditable financial workbooks headless via openpyxl.
evm
Read-only EVM client: wallets, tokens, gas across 8 chains.
hyperliquid
Hyperliquid market data, account history, trade review.