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 jingerzz/ai-investment-courses --skill spy-tlt-coursegit clone --depth 1 https://github.com/jingerzz/ai-investment-coursesWrote 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/jingerzz/ai-investment-courses/spy-tlt-course)<a href="https://agentmods.dev/skills/jingerzz/ai-investment-courses/spy-tlt-course"><img src="https://agentmods.dev/badge/skills/jingerzz/ai-investment-courses/spy-tlt-course/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/jingerzz/ai-investment-courses/spy-tlt-course"><img src="https://agentmods.dev/badge/skills/jingerzz/ai-investment-courses/spy-tlt-course.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 | $0.00136 | $0.01199 |
| Opus 5 | $0.00068 | $0.00600 |
| Sonnet 5 | $0.00027 | $0.00240 |
| Haiku 4.5 | $0.00014 | $0.00120 |
Grade A, and why
spy-tlt-course 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 12d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spy-tlt-course
Agent guidance for the course edition of the SPY/TLT strategy MCP server. The student installs and registers it via the course-setup skill; this skill explains how to use it once it's live.
Server fingerprint
- Server name (in Zo MCP registry):
spy-tlt-course - Tool count: 14 (course subset of the 37-tool production server)
- Source:
professional/servers/spy-tlt-course/ - Entry point:
uv run spy-tlt-server - Data: SPY + TLT daily prices via
yfinance, cached locally
If the tool count isn't 14 or the server isn't registered, route the student back to the course-setup skill.
When to invoke
The student is asking a question that requires a market-regime tool call — not narrative analysis. Examples:
- "What's today's signal?"
- "Are we in a Green day or Orange day?"
- "What's SPY doing right now?"
- "Is the strategy data fresh?"
- "Explain the current signal."
Do not invoke for: portfolio construction advice, trade execution, options strategy, or anything outside the SPY/TLT color-day framework. The course server is intentionally minimal.
The 6-step workhorse pattern
Every SPY/TLT question follows this pattern. Memorize it:
get_strategy_guide— call ONCE per session, first thing. Tells you what this strategy actually does.refresh_data— call before any market-data query. Pulls latest SPY + TLT prices.get_current_signal— returns today's color (Green / Orange / Blue / Red) + exposure target +stale_data_warning. Quote every field verbatim.explain_signal— call with the signal name from step 3. Returns the strategy's own explanation, not your interpretation.get_market_context— SPY/QQQ/IWM/DIA/RSP extension and breadth. Use when the student asks "is the market healthy?" or for cross-index context.- Cite the tool call when you answer. Format:
(via spy-tlt-course / get_current_signal).
Critical rules
- Quote tool output verbatim before interpreting. Phantom prices — numbers from training memory dressed up as "the latest" — are the failure mode this course is designed to break. If you can't name the tool call you got a number from, don't say the number.
- Pass through
stale_data_warningeven whennull. The student needs to see that field to learn the discipline. - Color days are exclusive — pick one, no hedging. "It's a Green day" not "it's Green-leaning."
- Refresh before reading. If the cached prices are >1 trading day old,
get_current_signalmay report a stale regime.refresh_datafirst, thenget_current_signal.
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.
- 12d ago First seen · 79 lines · 136 tokens per session scan A 327563953682
spy-tlt-course is a skill published in the GitHub repository jingerzz/ai-investment-courses (4 stars, last pushed 4mo ago), licensed MIT. It adds 136 tokens to every session and 1,199 once invoked, about $0.0007 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
common-sense-index-investing-bogle
Apply John Bogle index investing rules for low-cost funds, asset allocation, fees, taxes, ETFs, advisers, and buy-hold discipline.
stockbee-setup-fluency-trainer
Build a Stockbee-style setup model book from momentum-burst screener candidates, then update 3-day and 5-day forward outcomes with MFE/MAE, stop-hit status, outcome tags, and cohort statistics. Use when the user wants to study Stockbee Momentum Burst examples, track failed candidates, build setup fluency, review A/B…
grayscale-crypto-sectors
Use when evaluating crypto through a Grayscale-style Crypto Sectors lens: sector taxonomy, FTSE/Grayscale index eligibility, fee/usage fundamentals, sector-share valuation, ETP/trust wrappers, and Zcash-style privacy-as-money theses.
ansem-crypto
Use when evaluating crypto narratives, attention rotation, memecoin cycles, Solana-style ecosystem momentum, social distribution, and reflexive retail flows in an Ansem-style crypto market framework.
livermore
Use when evaluating trend-following trades, pivotal-point breakouts, pyramiding, stop discipline, or whether a liquid market is acting right in a Jesse Livermore style.
a16z-techno-optimist
Use when evaluating startups or tech platforms through an a16z-style lens: technology adoption, market creation, platform power, AI/crypto/software narratives, and bold long-duration tech bets.