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 ntaffzii/Skill-Agents --skill dividend-value-screenergit clone --depth 1 https://github.com/ntaffzii/Skill-AgentsWrote 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/ntaffzii/skill-agents/dividend-value-screener)<a href="https://agentmods.dev/skills/ntaffzii/skill-agents/dividend-value-screener"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/dividend-value-screener/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/ntaffzii/skill-agents/dividend-value-screener"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/dividend-value-screener.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 | $0.00097 | $0.00987 |
| Opus 5 | $0.00048 | $0.00494 |
| Sonnet 5 | $0.00019 | $0.00197 |
| Haiku 4.5 | $0.00010 | $0.00099 |
Grade A, and why
dividend-value-screener 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 11d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dividend / Value Screener
Overview
"Is this a good dividend stock?" needs more than a high yield number — a very high yield is often a warning sign (a "yield trap": price has fallen because the market expects a cut), not a bargain. This skill supplies the standard checklist of value/dividend-quality criteria and their common pitfalls, to apply against fundamental data the user provides or fetches separately.
Not financial advice. This is a screening framework, not a buy recommendation — passing every criterion here doesn't guarantee a good investment, and failing one doesn't automatically disqualify a stock.
When to use
- ประเมินหุ้นปันผลว่ามีสัญญาณ yield trap หรือไม่
- คัดกรองหุ้น value ด้วยเกณฑ์มาตรฐาน (P/E, D/E, payout ratio)
- Reviewing whether a dividend growth streak is intact and the payout ratio still looks sustainable
When NOT to use
- The task is a momentum/breakout swing-trade screen — this is a fundamentals-based value/income screen, structurally different from uptrend-analyzer's technical criteria
- No fundamental data is available and the user won't supply any — this skill needs P/E, yield, payout ratio, etc. as inputs; it doesn't fetch them
Core knowledge
Core checklist:
| Metric | What it checks | Common pitfall |
|---|---|---|
| Dividend yield | Income relative to price | A yield much higher than the stock's own history or its sector peers is a warning sign, not automatically a bargain — check why it's high before treating it as attractive |
| Payout ratio (dividend ÷ earnings) | Sustainability of the dividend | A payout ratio near or above 100% (paying out more than earned) is fragile — a cut is more likely under any earnings pressure. Note: payout ratio can look distorted for REITs/MLPs where GAAP earnings differ structurally from distributable cash flow — use the sector-appropriate cash-flow metric instead of raw payout ratio for those |
| Dividend growth streak | Consistency of dividend policy over time | A long streak is a positive signal about management discipline, but a streak alone doesn't guarantee it continues — check whether recent increases have been token-sized (e.g. $0.01) as a sign of strain |
| P/E ratio | Price relative to earnings | Compare within the same sector — "cheap" and "expensive" P/E norms vary enormously by industry; a low P/E can also mean the market correctly expects declining earnings, not that the stock is undervalued |
| Debt/Equity | Balance-sheet leverage | High leverage isn't automatically bad (capital-intensive sectors like utilities/REITs normally run higher D/E), but it does reduce a company's flexibility to maintain the dividend through a downturn — again, compare within sector |
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.
- 11d ago First seen · 52 lines · 97 tokens per session scan A 546e11a146cf
dividend-value-screener is a skill published in the GitHub repository ntaffzii/Skill-Agents (4 stars, last pushed 2d ago), licensed MIT. It adds 97 tokens to every session and 987 once invoked, about $0.0005 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
bionic-safety-net
Unified survival infrastructure: health, finance, legal safety, circuit breakers, and structural protection against all ruin classes. The last line of defense.
structural-trading-gate
Unified zero-emotion variance shield for capital markets (FX, crypto, CFDs) and poker. Absorbs trading-risk-gate + zenith-execution + trade-journal-analyzer into one engine.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
zenith-execution
Unified trade execution suite: Half-Kelly sizing, stop-loss calculation, Monte Carlo simulation, and portfolio rebalancing. Absorbs: kelly-mandate, stop-loss-calc, monte-carlo-sim, portfolio-rebalancer.
circuit-breaker
Mandatory systemic pause when cumulative red flags exceed threshold. Forces disengagement across Trading, Spending, Relationships, Work, and Energy domains.
market-brief
Generate a current morning market brief for Mick's indices, commodities, currencies, macro, and expanded crypto watchlist. Trigger immediately when the user starts with "mb" or asks for a market brief, morning brief, market update, pre-market summary, market open summary, or asks what the market is doing. Always…