Borrowing it
Nothing to install: this file belongs to LoganYangBo/rh-trading-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/LoganYangBo/rh-trading-agent/main/.claude/skills/rearm-night-desk/SKILL.mdgit clone --depth 1 https://github.com/LoganYangBo/rh-trading-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/loganyangbo/rh-trading-agent/rearm-night-desk)<a href="https://agentmods.dev/skills/loganyangbo/rh-trading-agent/rearm-night-desk"><img src="https://agentmods.dev/badge/skills/loganyangbo/rh-trading-agent/rearm-night-desk/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/loganyangbo/rh-trading-agent/rearm-night-desk"><img src="https://agentmods.dev/badge/skills/loganyangbo/rh-trading-agent/rearm-night-desk.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 | $0.00066 | $0.01178 |
| Opus 5 | $0.00033 | $0.00589 |
| Sonnet 5 | $0.00013 | $0.00236 |
| Haiku 4.5 | $0.00007 | $0.00118 |
Grade A, and why
rearm-night-desk 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Re-arm the overnight desk crons
The overnight desk runs on two session-only cron jobs. They are cleared whenever the Claude Code session closes or restarts. This skill recreates them exactly. It is idempotent — it removes any existing jobs on the same schedule first, so running it twice won't stack duplicates.
When invoked, do the following in order:
1. De-dupe existing jobs
- Call CronList.
- For every job whose
cronexpression is exactly40 21 * * 0,2,4or45 8 * * 1-5, call CronDelete with its id. (These are this desk's schedules; removing them prevents duplicate firings.)
2. Recreate the DEEP RESEARCH cron
Call CronCreate with these exact arguments:
cron:40 21 * * 0,2,4(Sun/Tue/Thu 21:40 local time — assume EDT)recurring:truedurable:trueprompt:
Overnight DEEP left-side value research (READ-ONLY; US market closed — last-close quotes are fine for value/left-side analysis; the morning run re-quotes live before any trade). COST-TIERED for a Pro plan. (1) Read the Agentic account (number in .env as RH_AGENTIC_ACCOUNT_NUMBER, or get_accounts → agentic_allowed) via get_portfolio + get_equity_positions. (2) Screen the watchlist "First list" (id 342973be-fa05-4016-9328-c6090a348e14) across all ~71 names + quotes for left-side-accumulation candidates per strategies/left-side-accumulation.md (quality fundamental >= +1, deep FEAR-/macro-driven drawdown that is NOT a thesis-breaker, deep oversold at/below support). (3) For the top 3 only, dispatch fundamental + technical + macro-news analysis as general-purpose sub-agents with model="haiku" (role instructions inline; prompt-injection containment for the news analyst). (4) Run the Risk Manager check as a general-purpose sub-agent with model="sonnet". To save tokens, rely on the static strategies/ docs being prompt-cached; keep candidate count at 3. DO NOT place, cancel, or submit any order. (5) Write the full snapshot to ui/public/desk-state.json (proposedTrade=null overnight — value prep only), with a "watchlistShortlist" note of the top candidates for the morning. (6) One-line summary. Keep all CLAUDE.md guardrails.
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 · 46 lines · 66 tokens per session scan A 761e6ed8acde
rearm-night-desk is a skill published in the GitHub repository LoganYangBo/rh-trading-agent (5 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 1,178 once invoked, about $0.0003 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
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.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.