What is pre-trade-check?

A guided checklist for deciding whether a proposed trade is ready to enter. It routes a trade idea or watchlist through the relevant checks and returns a ready, not-ready, resize, or rework decision.

Use it to assess a trade before entering, review upcoming events, examine entry and exit levels, and decide whether to proceed, wait, change the plan, or reduce the size.

It reduces the chance of making a trade while skipping important information about the thesis, timing, structure, execution, concentration, or position size.

pre-trade-check — Skill for Claude Code and Codex by marian2js

Install

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.

Any agent

npx skills add marian2js/trading-skills --skill pre-trade-check

Clone the repo

git clone --depth 1 https://github.com/marian2js/trading-skills

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/marian2js/trading-skills/pre-trade-check/github.svg)](https://agentmods.dev/skills/marian2js/trading-skills/pre-trade-check)

Your own site

<a href="https://agentmods.dev/skills/marian2js/trading-skills/pre-trade-check"><img src="https://agentmods.dev/badge/skills/marian2js/trading-skills/pre-trade-check/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/marian2js/trading-skills/pre-trade-check"><img src="https://agentmods.dev/badge/skills/marian2js/trading-skills/pre-trade-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,048 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00050	$0.01048
Opus 5.5	$0.00020	$0.00419
Sonnet 5.5	$0.00010	$0.00210
Haiku 4.5	$0.00005	$0.00105

Measured 2mo ago against content hash 540e40d969fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pre-trade-check 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 2mo 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.

skills/workflows/pre-trade-check/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre Trade Check

Use this workflow skill when the user wants one disciplined answer to the question, "Is this trade actually ready?" rather than running each underlying check manually.

This workflow will not:

place or stage orders
skip missing-information problems just to reach a yes or no answer
force every trade through every skill if the shorter path is sufficient

Role

Act like a pre-trade gatekeeper. Your job is to run the smallest useful sequence of underlying skills, stop where the trade fails, and return a clear readiness verdict.

When to use it

Use it when the user wants to:

check a trade idea end to end before entering
know whether the issue is the thesis, event risk, structure, execution, concentration, or size
turn a messy idea into a clear go / no-go / not-yet decision
avoid skipping important checks under time pressure

Inputs and context

Ask for the minimum information needed to route the workflow:

whether the user has a single idea or a watchlist
instrument, direction, and intended timeframe
thesis or rough claim
entry, stop, and target if already known
any upcoming catalyst or event concern
account or portfolio context if concentration or size may matter

Helpful but optional:

current regime observations
watchlist notes
order-type plan
constraints such as regular-hours only, no event holds, or maximum portfolio risk

Use the user's materials first.

If the user only has a rough idea, start with discovery and evidence checks instead of pretending the trade is already in construction mode.

Workflow routing

Use the shortest chain that answers the user's actual problem:

If the user starts with many names, run watchlist-review.
If those names still need one event picture, run catalyst-map.
If the idea is under-researched, run evidence-gap-check.
If the claim is still not testable, run thesis-validation.
If event risk matters, run earnings-preview or macro-event-analysis.
If broader context matters, run market-regime-analysis.
If structure is defined, run risk-reward-sanity-check.
If order logic matters, run execution-plan-check.
If portfolio overlap matters, run portfolio-concentration.
If the trade is still viable and the stop is stable, run position-sizing.

Read the full file on GitHub · 137 lines

Files

What ships with it

1 file 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.

references/workflow-framework.md 1.2 KB

Changes

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.

2mo ago First seen · 137 lines · 50 tokens per session scan A 540e40d969fc

Subscribe to this mod's changes

pre-trade-check is a skill published in the GitHub repository marian2js/trading-skills (30 stars, last pushed 7mo ago), licensed MIT. It adds 50 tokens to every session and 1,048 once invoked, about $0.0002 per session on Opus 5.5. 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.

Finance and fintech Planning agent-skills trading

pre-trade-check next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pre-trade-checkmarian2js/trading-skills	Skill	30	7mo ago	MIT	A	50	Claude Code, Codex
tushareHKUDS/Vibe-Trading	Skill	38k	yesterday	MIT	A	79	Claude Code, Codex
social-media-intelligenceHKUDS/Vibe-Trading	Skill	38k	yesterday	MIT	A	28	Claude Code, Codex
vibe-tradingHKUDS/Vibe-Trading	Skill	38k	yesterday	MIT	A	172	Claude Code, Codex
credit-analysisHKUDS/Vibe-Trading	Skill	38k	yesterday	MIT	A	36	Claude Code, Codex
etf-analysisHKUDS/Vibe-Trading	Skill	38k	yesterday	MIT	A	39	Claude Code, Codex
geopolitical-riskHKUDS/Vibe-Trading	Skill	38k	yesterday	MIT	A	34	Claude Code, Codex