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/kay-ou/claudeskills/ptrade-devnpx skills add kay-ou/ClaudeSkills --skill ptrade-devgit clone --depth 1 https://github.com/kay-ou/ClaudeSkillsWrote 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/kay-ou/claudeskills/ptrade-dev)<a href="https://agentmods.dev/skills/kay-ou/claudeskills/ptrade-dev"><img src="https://agentmods.dev/badge/skills/kay-ou/claudeskills/ptrade-dev.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 | $0.00126 | $0.03139 |
| Opus 5 | $0.00063 | $0.01570 |
| Sonnet 5 | $0.00025 | $0.00628 |
| Haiku 4.5 | $0.00013 | $0.00314 |
Grade A, and why
ptrade-dev 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 3d 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 — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PTrade Strategy Development Skill
You are writing code for the PTrade quantitative trading platform or its local simulator SimTradeLab. This skill ensures you NEVER make API errors by providing the complete reference inline.
CRITICAL PLATFORM CONSTRAINTS
These constraints apply to ALL code that runs on PTrade (NOT local-only files like research/run_local_backtest.py):
-
NO f-strings — Use
%formatting or.format(). PTrade's Python does not support f-strings.# WRONG log.info(f"price: {price}") # CORRECT log.info("price: %s" % price) log.info("price: {}".format(price)) -
NO
import ioorimport sys— These modules are blocked on PTrade. -
NO walrus operator
:=— Not supported. -
NO
match/case— Not supported. -
Code format: PTrade uses
.SS(Shanghai) and.SZ(Shenzhen) suffixes, but Order objects return.XSHG/.XSHEsuffixes. Be aware of this difference. -
Global object
g: Useg.xxxfor cross-function state. Variables starting with__are private and won't be persisted. -
logobject: Uselog.info(),log.warning(),log.error()etc. Neverprint().
STRATEGY LIFECYCLE (MANDATORY KNOWLEDGE)
A strategy has exactly 2 required functions and 5 optional ones:
initialize(context) # REQUIRED — runs once at startup
handle_data(context, data) # REQUIRED — runs every bar (daily/minute)
before_trading_start(context, data) # optional — runs before market open
after_trading_end(context, data) # optional — runs after market close
tick_data(context, data) # optional — runs every 3s (live trading only)
on_order_response(context, order_list) # optional — order callback (live only)
on_trade_response(context, trade_list) # optional — trade callback (live only)
Lifecycle Timing
- initialize: runs ONCE at strategy start
- before_trading_start: backtest 8:30, live 9:10 (configurable)
- handle_data: backtest 9:31-15:00 (minute) or 15:00 (daily); live 9:30-14:59
- after_trading_end: ~15:30
- tick_data: 9:30-14:59, every 3s (live only)
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.
- 3d ago First seen · 305 lines · 126 tokens per session scan A b396932247f6
ptrade-dev is a skill published in the GitHub repository kay-ou/ClaudeSkills (11 stars, last pushed 5mo ago), licensed MIT. It adds 126 tokens to every session and 3,139 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
invoice-organizer
Automatically organizes invoices and receipts for tax preparation by reading messy files, extracting key information, renaming them consistently, and sorting them into logical folders. Turns hours of manual bookkeeping into minutes of automated organization.
convex-add
Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability…
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.
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…