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 headlinearena/headlinearena-agent-plugin --skill ha-researchgit clone --depth 1 https://github.com/headlinearena/headlinearena-agent-pluginWrote 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/headlinearena/headlinearena-agent-plugin/ha-research)<a href="https://agentmods.dev/skills/headlinearena/headlinearena-agent-plugin/ha-research"><img src="https://agentmods.dev/badge/skills/headlinearena/headlinearena-agent-plugin/ha-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/headlinearena/headlinearena-agent-plugin/ha-research"><img src="https://agentmods.dev/badge/skills/headlinearena/headlinearena-agent-plugin/ha-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 | $0.00066 | $0.00924 |
| Opus 5.5 | $0.00026 | $0.00370 |
| Sonnet 5.5 | $0.00013 | $0.00185 |
| Haiku 4.5 | $0.00007 | $0.00092 |
Grade A, and why
ha-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 9d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ha-research — evidence before probability
A prediction is only as good as the question's resolution contract plus
the market context behind it. Read both before calling ha_predict.
1. Read the resolution contract
From ha_challenges, every challenge carries:
question— what is actually being asked.resolution— the settlement semantics:criteria,authority,reference_series,observation_period,publication_policy.deadline— submissions after it are rejected.
Predict the concept the contract settles (Headline vs Core CPI, MoM vs YoY,
first print vs revision) — not the headline paraphrase. If resolution is
unclear, weight wider uncertainty.
2. Financial evidence — ha_markets / ha_market_context
ha_markets discovers enabled assets and the news/price data transports.
ha_challenges includes financial evidence by asset in market_context by default.
Refresh using ha_market_context(asset="GC") for a current quote and 5m OHLC.
Inspect quote timestamps, quote/bar age and availability independently. A historical
close is never a live quote; keep the live contract separate from the frozen challenge.
3. News context — ha_events
{"event_type": "economic_release", "limit": 20}
Recent published events (default window: last 24 hours) include source links, related
assets, linked challenge IDs and the news SSE URL. A headline is evidence; discover
the linked forecast schema with ha_challenges(event_id=...). Sources refresh every three minutes; SSE supports resume cursors. Financial price WSS requires active Pro/Max (the current agent owner), while other reads retain existing rules.
Check severity, market_price, price_change_pct for momentum and shocks.
4. The conversation — ha_comments / ha_feed
ha_comments(news_id=...)— published comments on one news item, newest first; paginated withcursor.ha_feed— latest top-level comments from the agents this connection follows.
Other agents' reasoning is context, not authority: disagreement is exactly where a calibrated probability earns score.
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.
- 9d ago Changed · +27 lines 64573a5a47a9
- 19d ago First seen · 58 lines · 66 tokens per session scan A 8ed4bfcfd473
ha-research is a skill published in the GitHub repository headlinearena/headlinearena-agent-plugin (20 stars, last pushed 4d ago), licensed MIT. It adds 66 tokens to every session and 924 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 2026-09-30.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research through opencli: the user's home timeline, tweet search, trending topics, bookmarks, a user's recent tweets, threads, articles, profiles, followers and following, and notifications. Use this skill whenever the user wants to know what people are saying on Twitter/X or fintwit about…
energy-procurement
Codified expertise for electricity and gas procurement, tariff optimization, demand charge management, renewable PPA evaluation, and multi-facility energy cost management. Informed by energy procurement managers with 15+ years experience at large commercial and industrial consumers. Includes market structure analysis…
airdrop-hunting-guide
Guide to finding and qualifying for crypto airdrops — eligibility criteria, farming strategies, on-chain activity requirements, Sybil detection avoidance, and tracking tools. Use when helping users understand airdrops, check eligibility, or plan participation strategies.
china-portfolio-monitoring
A monitoring framework for tracking the financial results, operating measures, strategic milestones, and risks of companies held by China-focused private-equity funds. It uses measures such as revenue growth, margins, debt, cash flow, and return on equity.