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 skloxo/TideTrading --skill bottleneck-huntergit clone --depth 1 https://github.com/skloxo/TideTradingWrote 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/skloxo/tidetrading/bottleneck-hunter)<a href="https://agentmods.dev/skills/skloxo/tidetrading/bottleneck-hunter"><img src="https://agentmods.dev/badge/skills/skloxo/tidetrading/bottleneck-hunter/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/skloxo/tidetrading/bottleneck-hunter"><img src="https://agentmods.dev/badge/skills/skloxo/tidetrading/bottleneck-hunter.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 | $0.00145 | $0.02683 |
| Opus 5 | $0.00072 | $0.01341 |
| Sonnet 5 | $0.00029 | $0.00537 |
| Haiku 4.5 | $0.00015 | $0.00268 |
Grade A, and why
bottleneck-hunter 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.
This is a copy
100% identical to bottleneck-hunter — 0 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Supply-Chain Bottleneck Hunter
Decompose a super-trend (user-specified, e.g. "AI infrastructure", "energy transition") into its physical supply chain and hunt for bottleneck-arbitrage opportunities.
Core Idea
Don't ask "which AI stock to buy" — ask "if this trend keeps expanding, which link runs out first?"
Traditional research chases leaders and known tracks. This skill inverts: start from the choke points of the physical supply chain and find companies nobody notices but that the whole industry must wait on when they run short.
The edge: Layer-1 bottlenecks (GPU, HBM, power) are already priced in. The real alpha is in Layer 2 and Layer 3 — optical modules, lasers, InP substrates, SOI wafers, epitaxy equipment, wafer-level test, IC substrates, specialty fiberglass.
Step 1: Super-Trend Confirmation
Trend Filter Criteria
| Criterion | Requirement | How to verify |
|---|---|---|
| Durability | ≥3-5 years of certain growth | Search industry forecasts, capex plans |
| Physicality | Needs real hardware/material/equipment build | Distinguish "software upgrade" from "physical expansion" |
| Scale | Global capex >$50B/year | Search top players' capex guidance |
| Acceleration | Demand growth > supply expansion | Compare demand growth vs capacity plans |
Use web_search to verify. Reference super-trends: AI infrastructure, energy transition (nuclear/grid/storage), defense modernization, semiconductor reshoring, space economy.
Step 2: Physical Supply-Chain Decomposition
Don't stop at concepts — decompose to physical entities.
Layer 0 (end): final product/service
Layer 1 (core component): already closely watched → priced in, limited alpha
Layer 2 (sub-component/material): low attention, alpha-rich
Layer 3 (upstream equipment/raw material)
Layer 4 (infrastructure): power, cooling, land, talent, certifications
AI Infrastructure Example
Layer 0: AI model training/inference services
Layer 1: GPU/accelerators, HBM, servers, data centers
Layer 2 (focus zone):
- Network interconnect: optical modules, fiber, switch ASICs, copper cables
- Optical comms core: lasers (EML/VCSEL/CW), modulators, photodetectors
- Semiconductor materials: InP substrates, GaAs substrates, SOI wafers, SiC substrates
- Advanced packaging: CoWoS interposers, HBM TSV, ABF substrate film
- PCB/substrate: high-frequency PCB, IC substrates, specialty fiberglass
- Test: wafer-level test (probe cards), burn-in, ATE
- Thermal/cooling: liquid cooling, CDU, immersion fluid
- Power connection: busbars, UPS, distribution, transformers
Layer 3: epitaxy equipment (MOCVD/MBE), lithography/etch, high-purity metals (In/Ga/Ge), specialty gases, sputtering targets, certifications (MSA/Telcordia)
Layer 4: power (nuclear/gas/transmission), cooling water, data-center land/permits
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 First seen · 191 lines · 145 tokens per session scan A 2b8063b29992
bottleneck-hunter is a skill published in the GitHub repository skloxo/TideTrading (10 stars, last pushed 2d ago), licensed MIT. It adds 145 tokens to every session and 2,683 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to bottleneck-hunter, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
daily-deep-brief
A scheduled, pre-market investment briefing for Hong Kong and United States stocks. A deterministic preparation step gathers data and an agent adds judgment, while a later step validates and publishes the result.
hk-stock-analysis
A workspace-aware analysis workflow for Hong Kong-listed stocks. It retrieves prices, technical indicators, market comparisons, and news through a local data pipeline, then adds Hong Kong-specific investment context.
us-stock-analysis
Workspace-aware US stock analysis for kcn. Routes through clawock analyze-us / clawock us-quotes instead of generic web search, then layers fundamental/technical/news analysis on top. Use when user asks to analyze a US ticker (e.g. "analyze AAPL", "look at RKLB", "compare TSLA vs NVDA"), check earnings, run…
invest-analyst
A framework for producing professional investment research, including company reports, industry studies, event analysis, analyst-expectation reviews, comparisons, and market summaries. It connects several investment research workflows into one process.
invest-fund
A Chinese-language guide for analysing investment funds, with different workflows for comparing funds, reviewing ETFs, examining new funds, and studying industry funds.
invest-cli
An investment-analysis command-line tool that fetches data for Chinese stocks and funds, US stocks, and stock screening, then applies matching analysis frameworks. A command-line tool is a program operated from a terminal.