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 lanfuli/aleabito-serenity-skills --skill serenity-radargit clone --depth 1 https://github.com/lanfuli/aleabito-serenity-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/lanfuli/aleabito-serenity-skills/serenity-radar)<a href="https://agentmods.dev/skills/lanfuli/aleabito-serenity-skills/serenity-radar"><img src="https://agentmods.dev/badge/skills/lanfuli/aleabito-serenity-skills/serenity-radar/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/lanfuli/aleabito-serenity-skills/serenity-radar"><img src="https://agentmods.dev/badge/skills/lanfuli/aleabito-serenity-skills/serenity-radar.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 | $0.00188 | $0.01655 |
| Opus 5 | $0.00094 | $0.00827 |
| Sonnet 5 | $0.00038 | $0.00331 |
| Haiku 4.5 | $0.00019 | $0.00166 |
Grade A, and why
serenity-radar scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Serenity Radar
A data-driven companion to serenity-method. Where serenity-method teaches how she analyzes, this skill uses her actual 11-month archive (2025-07-02 → present, ~6,120 posts / 750 tickers) to estimate where her attention is going and to generate candidates the way she would.
What this is NOT. Not a predictor, not a buy/sell signal, not "she will pump X next." It is a candidate generator + checklist. A single account is fragile; virality ≠ correctness; her archive has survivorship bias (winners get re-cited, losers fade). Read the Caveats section before using output. Always end with: 仅作信息跟踪，不构成投资建议。
Prerequisites
- The mention archive must exist (the
follow-aleabitoskill produces it). Default path:$FOLLOW_ALEABITO_REPORTS_DIR/aleabito-mentions-events.csv(else the workspacereports/). - Keep it current with
follow-aleabito's incremental fetch (analyze-mentions.js --incremental --resume) before running radar, so signals reflect the latest days. - For the analytical gate, use the local
serenity-methodskill.
Mode 1 — RADAR (data-driven, run this first)
Run the signal extractor:
FOLLOW_ALEABITO_REPORTS_DIR="<reports dir>" node skills/serenity-radar/scripts/radar.js --window 14 --top 20
# add --json for machine-readable output; --asof YYYY-MM-DD to evaluate a past date; --window 7 for a tighter read
It prints four signal blocks (see references/signals.md for the exact math):
- 🔥 Heating — tickers whose mention count is accelerating (recent window vs prior window). This is the core "she's ramping attention here" signal.
- 🆕 New entrants — tickers that first appeared within the window. Candidate next focus — she often seeds a name quietly, then ramps.
- 🎯 Conviction watch — high recent volume + sustained + still active. Her core book right now (defended, repeated).
- 🔄 Theme rotation — theme mention-share recent vs prior. Tells you which narrative she is rotating into / out of.
What ships with it
3 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.
- 12d ago First seen · 68 lines · 188 tokens per session scan A 4ce7bdcb58ad
serenity-radar is a skill published in the GitHub repository lanfuli/aleabito-serenity-skills (94 stars, last pushed 3mo ago), licensed MIT. It adds 188 tokens to every session and 1,655 once invoked, about $0.0009 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
irpf-brasil
Assistente especializado em Imposto de Renda Pessoa Física (IRPF) Brasil — ciclo 2026, ano-base 2025. Use quando o usuário mencionar "IRPF", "Imposto de Renda", "declaração de IR", "malha fina", "DARF", "REVAR", "Cashback IRPF", "pré-preenchida", "Núcleo Familiar", "restituição IR", "bets imposto", "ComprovaBet"…
guizang-social-card-skill
Generate Guizang-style social card image sets, Live Photo motion cards, material-first Live Photo puzzle layouts, triple Live Photo collages, long-video-to-Live-Photo treatments, and WeChat official account cover pairs from articles, scripts, screenshots, product notes, subtitles, photos, or user-supplied videos. Use…
national-team-position
A Chinese-language analysis tool that estimates changes in China’s government-backed ETF holdings by tracking ETF share counts and related index prices. ETFs are funds traded on stock exchanges, and the “national team” refers here to Central Huijin, a state investment company.
deepread-bank-statements
Extract structured data from bank statements — account holder, period, opening/closing balances, and every transaction as typed JSON. Works on PDF and scanned statements from any bank. Per-field confidence flags. PII redaction for compliant sharing. Free 2,000 pages/month.
deepread-invoice
Extract structured data from invoices, receipts, and bills using DeepRead. Pre-built schemas for vendor, line items, totals, tax, due dates. 97%+ accuracy with human-in-the-loop flags. Free 2,000 pages/month.
deepread-pay-stubs
Extract structured data from pay stubs and earnings statements — employer, employee, pay period, gross/net pay, taxes, deductions, and YTD totals — as typed JSON. Ideal for income verification and lending. Per-field confidence flags. PII redaction built in. Free 2,000 pages/month.