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 skills/aaronjmars/aeon-agent/crypto-trackernpx skills add aaronjmars/aeon-agent --skill crypto-trackergit clone --depth 1 https://github.com/aaronjmars/aeon-agentWrote 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/aaronjmars/aeon-agent/crypto-tracker)<a href="https://agentmods.dev/skills/aaronjmars/aeon-agent/crypto-tracker"><img src="https://agentmods.dev/badge/skills/aaronjmars/aeon-agent/crypto-tracker.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 5.1 | $0.00000 | $0.00826 |
| Opus 5 | $0.00000 | $0.00413 |
| Sonnet 5 | $0.00000 | $0.00165 |
| Haiku 4.5 | $0.00000 | $0.00083 |
Grade A, and why
crypto-tracker scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf -H "x-cg-pro-api-key: $COINGECKO_API_KEY" "$URL" > .token-cache.json This is a copy
100% identical to [REPLACE: SKILL_NAME] — 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: [REPLACE: SKILL_NAME] description: Price and volume tracker for [REPLACE: TOKEN_SYMBOL] with anomaly alerts above [REPLACE: ALERT_THRESHOLD_PCT]% movement metadata: category: crypto var: "" tags: - crypto requires: - COINGECKO_API_KEY?
${var} — Optional. Pass a different CoinGecko ID to override the default. If empty, tracks the configured token.
Today is ${today}. Track [REPLACE: TOKEN_SYMBOL] price/volume and alert on anomalies.
Steps
-
Fetch current state — query CoinGecko for the latest price, 24h change, 24h volume. Use
COINGECKO_API_KEYif set, else the keyless endpoint:ID="${var:-[REPLACE: COINGECKO_ID]}" if [ -n "${COINGECKO_API_KEY:-}" ]; then URL="https://pro-api.coingecko.com/api/v3/simple/price?ids=$ID&vs_currencies=usd&include_24hr_change=true&include_24hr_vol=true" curl -sf -H "x-cg-pro-api-key: $COINGECKO_API_KEY" "$URL" > .token-cache.json else URL="https://api.coingecko.com/api/v3/simple/price?ids=$ID&vs_currencies=usd&include_24hr_change=true&include_24hr_vol=true" curl -sf "$URL" > .token-cache.json fiIf a
curlGET is flaky, use WebFetch on the same URL as a fallback (there is no network sandbox — WebFetch is just a convenience for flaky public reads). -
Read prior state — last 7 days of
memory/logs/YYYY-MM-DD.mdfor previous prices and volumes (parse lines like**[REPLACE: TOKEN_SYMBOL]**: price=$N, volume_24h=$N). -
Detect anomalies — flag if
|price_change_24h| >= [REPLACE: ALERT_THRESHOLD_PCT]%OR if 24h volume is>= 2xthe 7-day median. -
Write
output/articles/[REPLACE: SKILL_NAME]-${today}.mdwith:- Current price, 24h change, 24h volume
- 7-day price chart (sparkline as
▁▂▃▅▇characters) - Anomaly verdict:
QUIET/STEADY/ANOMALY(and which fired) - Links: CoinGecko page, Etherscan / explorer page if you know the contract address
-
Notify — if
ANOMALY, send via./notifywith the verdict + 1-2 sentences of context. Stay silent on QUIET/STEADY days. -
Log — append to
memory/logs/${today}.md:## [REPLACE: SKILL_NAME] - **[REPLACE: TOKEN_SYMBOL]**: price=$N, change_24h=$N%, volume_24h=$N - **Verdict**: QUIET | STEADY | ANOMALY:price | ANOMALY:volume
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.
- 6d ago First seen · 61 lines · 0 tokens per session scan A ba349bc6aa5e
crypto-tracker is a skill published in the GitHub repository aaronjmars/aeon-agent (11 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 826 tokens. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to [REPLACE: SKILL_NAME], differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
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
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
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.