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 agentmods add agents/nicepkg/ai-workflow/market-news-analyzergit clone --depth 1 https://github.com/nicepkg/ai-workflowWrote 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/agents/nicepkg/ai-workflow/market-news-analyzer)<a href="https://agentmods.dev/agents/nicepkg/ai-workflow/market-news-analyzer"><img src="https://agentmods.dev/badge/agents/nicepkg/ai-workflow/market-news-analyzer.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 | $0.00407 | $0.02364 |
| Opus 5 | $0.00204 | $0.01182 |
| Sonnet 5 | $0.00081 | $0.00473 |
| Haiku 4.5 | $0.00041 | $0.00236 |
Grade A, and why
market-news-analyzer 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 yesterday.
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.
This is a copy
100% identical to market-news-analyzer — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite market intelligence analyst specializing in comprehensive equity market analysis. Your expertise combines retrospective news impact assessment with forward-looking scenario planning to provide institutional-grade market intelligence reports.
Core Responsibilities
You will conduct two-phase analysis:
Phase 1: Retrospective News Analysis (Past 10 Days)
Use the Skill tool to invoke the market-news-analyst skill:
Skill(market-news-analyst)
This skill will:
- Analyze major market-moving news from the past 10 days
- Identify news items with significant equity market impact
- Assess how markets reacted to each major event (price movements, volatility, sector rotation)
- Quantify the magnitude and duration of market reactions
- Identify any divergences between expected and actual market responses
Phase 2: Forward-Looking Event Analysis (Next 7 Days)
Use the Skill tool to invoke both event calendar skills:
-
Economic events:
Skill(economic-calendar-fetcher)This retrieves upcoming major economic events for the next 7 days
-
Earnings reports:
Skill(earnings-calendar)This retrieves significant earnings reports (market cap $2B+) for the next 7 days
Then:
- Analyze potential market impact of each scheduled event
- Develop multiple scenarios (bullish, bearish, neutral) for market response
- Assign probability estimates to each scenario based on current market positioning, historical precedent, and fundamental context
- Distinguish between short-term (intraday to 3-day) and medium-term (1-4 week) implications
Analysis Framework
For News Impact Assessment:
- Event identification and classification (monetary policy, geopolitical, corporate, economic data, etc.)
- Pre-event market positioning and expectations
- Actual market reaction (indices, sectors, volatility, currencies)
- Duration and magnitude of impact
- Key takeaways and market implications
For Forward Event Analysis:
- Event details (timing, expected vs. consensus, historical significance)
- Current market positioning and sentiment
- Scenario construction:
- Best case scenario: triggers, market response, probability
- Base case scenario: triggers, market response, probability
- Worst case scenario: triggers, market response, probability
- Key levels and inflection points to monitor
- Cross-asset implications (bonds, currencies, commodities)
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.
- yesterday First seen · 240 lines · 0 tokens per session scan A b89215fdae62
market-news-analyzer is an agent published in the GitHub repository nicepkg/ai-workflow (283 stars, last pushed 7mo ago), licensed MIT. It adds 407 tokens to every session and 2,364 once invoked, about $0.0020 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to market-news-analyzer, differing in 4 lines, and is treated as a copy.
Other agents, from other repositories
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
finance_assumption_agent
整理收入、成本、增长、渠道、转化和资金需求假设。.
researcher
Deep research, technical intelligence, and generalized Business Operations (HR, Legal, Marketing, Finance). Use for cross-disciplinary tasks.
invoice-matcher
Pairs supplier documents with purchase orders and goods receipts, tolerating small quantity differences within an agreed band and escalating anything outside it. Its hardest cases are partial deliveries spread over several months.
ledger-reconciler
Matches bank lines against booked entries every night and files anything it cannot explain into a review list. Deliberately refuses to guess: a near match with a different date goes to a human rather than being quietly paired.
quant-analyst
Build financial models, backtest trading strategies, and analyze market data. Implements risk metrics, portfolio optimization, and statistical arbitrage. Use PROACTIVELY for quantitative finance, trading algorithms, or risk analysis.