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 mphinance/alpha-skills --skill coil-scangit clone --depth 1 https://github.com/mphinance/alpha-skillsWrote 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/mphinance/alpha-skills/coil-scan)<a href="https://agentmods.dev/skills/mphinance/alpha-skills/coil-scan"><img src="https://agentmods.dev/badge/skills/mphinance/alpha-skills/coil-scan/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/mphinance/alpha-skills/coil-scan"><img src="https://agentmods.dev/badge/skills/mphinance/alpha-skills/coil-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00111 | $0.01710 |
| Opus 5 | $0.00056 | $0.00855 |
| Sonnet 5 | $0.00022 | $0.00342 |
| Haiku 4.5 | $0.00011 | $0.00171 |
Grade A, and why
coil-scan 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coil Scan — dual-timeframe %R Trend Exhaustion
Mirrors the "%R Trend Exhaustion [upslidedown]" TradingView indicator (dual timeframe 21 + 112). Finds stocks that are both deeply oversold AND just starting to reverse.
The indicator math
- %R(n) = Williams %R =
100 * (close - highestHigh_n) / (highestHigh_n - lowestLow_n), range −100…0. - Fast leg = EMA(7) of %R(21).
- Slow leg = EMA(3) of %R(112).
- Threshold (TH) = −80.
- In the coil: both fast AND slow ≤ −80. The short-term AND the structural picture are both deeply oversold. This is the stalk zone — a name can sit here for days/weeks before the trigger fires.
- Triggered out: fast crossed back above −80 while it was recently (within ~20 bars) coiled on both legs. The slow leg still lagging confirms the structural exhaustion hasn't reset — this is the bullish reversal signal.
Two output buckets
⚡ TRIGGERED OUT (≤3 days ago)
Fast just crossed back above −80. These are actionable reversal candidates.
A sanity check filters false-positives:
- If the close is already >5% above the price on the trigger date → tagged "already ran — not fresh" and downranked.
- If the close is now above EMA21 → same tag.
The canonical false-positive this catches: SLB crossed up but had already run +4% to just under its 21EMA by the time the scan ran — that's a chase, not an entry. It lands in the sanity-filtered section, not the fresh list.
🟢 IN THE COIL (stalk candidates)
Both legs ≤ −80, no trigger yet. Sorted deepest-first (most negative slow leg = most structurally exhausted).
The days-in-coil counter comes from the persistent state file
(state/coil_watch.json), so the scan can say "IREN — day 6 in the coil."
A name stays in the store until it triggers or exits the coil entirely.
Per-name display
SYM fast%R slow%R depth close day-in-coil vs SMA200 vs EMA21
IREN -92.3 -88.1 -8.1 $7.42 day 3 below SMA200 below EMA21
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 160 lines · 111 tokens per session scan A 116de683c820
coil-scan is a skill published in the GitHub repository mphinance/alpha-skills (21 stars, last pushed 11d ago), licensed MIT. It adds 111 tokens to every session and 1,710 once invoked, about $0.0006 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 2026-08-30.
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 using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
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.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.