tcx-risk

tcx-risk is a skill for Claude Code, Codex from monarchjuno/tradingcodex. It costs 38 tokens per session (603 once invoked), scanned A, original, Apache-2.0.

An investment and order risk review guide for checking a proposed trade before it is created or approved. It considers possible losses, position size, liquidity, volatility, concentration, policy limits, and missing market information.

In plain words
What is it for?
Use it to review stocks, funds, crypto, options, credit, and other trades; assess downside scenarios; and decide whether to approve, revise, or reject an order.
Why use it?
It helps identify unsafe or incomplete trade proposals, including stale prices, broker mismatches, unclear instruments, and risks that differ by asset type.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/monarchjuno/tradingcodex/tcx-risk
Any agent
npx skills add monarchjuno/tradingcodex --skill tcx-risk
Clone the repo
git clone --depth 1 https://github.com/monarchjuno/tradingcodex

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.

agentmods badge for tcx-risk

README.md
[![agentmods](https://agentmods.dev/badge/skills/monarchjuno/tradingcodex/tcx-risk.svg)](https://agentmods.dev/skills/monarchjuno/tradingcodex/tcx-risk)
Your own site
<a href="https://agentmods.dev/skills/monarchjuno/tradingcodex/tcx-risk"><img src="https://agentmods.dev/badge/skills/monarchjuno/tradingcodex/tcx-risk.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 603 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.00603
Opus 5 $0.00019 $0.00302
Sonnet 5 $0.00008 $0.00121
Haiku 4.5 $0.00004 $0.00060

Measured 5d ago against content hash b4075b332f03, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tcx-risk 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 5d 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.

workspace_templates/modules/repo-skills/files/.tradingcodex/subagents/skills/risk-manager/tcx-risk/SKILL.md · 58 lines

What it actually says

Review Risk

Use this skill before order ticket creation, approval, sizing/hedge decisions, or policy-sensitive escalation.

Codex-native state access:

  • Prefer TradingCodex MCP read/status tools such as get_order_ticket, list_broker_connections, get_broker_connection_status, get_portfolio_snapshot, and list_reconciliation_runs.
  • Treat failed checks, stale market state, broker drift, missing instrument mapping, and reconciliation mismatch as explicit approval-readiness blockers or warnings.

Universe method:

  • Identify asset universe, instrument, intended exposure, unwanted risk, and installed workflow support.
  • For public equity and ETF/index, review downside, catalyst risk, drawdown, stress scenarios, liquidity, concentration, factor/sector exposure, tail risk, and policy constraints.
  • For crypto, macro/rates/FX/commodities, options, credit signals, and cross-asset overlays, name instrument-specific risk inputs that are missing, such as funding, roll, duration, basis, venue, custody, borrow, margin, spread, or Greeks.
  • Use VaR/CVaR, scenario loss, or stress language only when the data and assumptions are explicit; otherwise name the missing inputs.
  • If the universe or instrument is not supported by installed skills, data, policy, and adapter boundaries, classify as not-decision-ready or blocked.

Expected output:

  • Universe, instrument, and risk posture
  • Downside case
  • Thesis break conditions
  • Position sizing limit
  • Liquidity and volatility risk
  • Stress, drawdown, tail-risk, VaR/CVaR, or scenario-loss notes when supportable
  • Policy constraints
  • Approval readiness concerns
  • Go, revise, or reject recommendation
  • Source/as-of posture and implementation-readiness gaps

Decision quality fields when applicable:

  • evidence_grade, source_freshness, source_quality
  • decision_quality_required, decision_readiness, confidence
  • investor_context_gate_required, investor_context_gaps
  • forecast_required, forecast_allowed, forecast_block_reason
  • contrary_evidence, update_triggers, invalidation_conditions

Role-specific quality:

  • State the largest failure mode first.
  • Distinguish investment risk, portfolio risk, policy risk, and execution risk.
  • Include support gap, stale data, or missing source status when it changes readiness.
  • Include explicit stop/revisit conditions when the user asks for decision support.
  • Lower confidence when data quality, sample size, regime coverage, or validation setup is weak.
  • Give a clear go, revise, reject, or blocked state with reasons.

Write outputs under trading/reports/risk/.

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.

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.

  1. 5d ago First seen · 58 lines · 38 tokens per session scan A b4075b332f03

Subscribe to this mod's changes

tcx-risk is a skill published in the GitHub repository monarchjuno/tradingcodex (366 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 603 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

agent-trading-predictor

Agent skill for trading-predictor - invoke with $agent-trading-predictor.

ruvnet/ruflo · 24 tokens

agent-agentic-payments

Agent skill for agentic-payments - invoke with $agent-agentic-payments.

ruvnet/ruflo · 22 tokens

agent-payments

Agent skill for payments - invoke with $agent-payments.

ruvnet/ruflo · 15 tokens

company-research

A 股个股研究六阶段 SOP(profile → financials → estimates → valuation → risk → report),Phase 0 范围 = 财务估值闭环。当任务是研究 / 分析 / 评估一只或多只已指定代码的 A 股个股时使用;规定每阶段取哪些数据、调哪些 calc 函数、必须落盘什么产物、过什么 Gate。不用于:从市场中筛选标的、泛行业讨论、概念解释、给投资动作建议。.

simonlin1212/Vibe-Research · 115 tokens

data-access

A 股零鉴权取数手册。当需要真实的行情 / 市值 / 估值快照、季度报告期累计财务数据、机构一致预期 EPS、PE 历史序列、公告标题、日 K 线、交易日历时使用;只允许运行本 skill 登记的脚本取数(腾讯 / 新浪 / 同花顺 / baostock / 深交所 / 东财),禁止凭模型记忆给数,禁止自造爬虫。概念解释、观点讨论等不需要取数的话题不要加载。.

simonlin1212/Vibe-Research · 127 tokens

industry-chain

产业链下钻与不可替代性判定方法:以龙头为"需求入口"沿供应链逐层下钻(整机 / 龙头 → 部件 → 核心器件 → 材料 → 衬底与设备),用物理 / 材料约束(扩产周期、良率、认证周期、有无替代)当筛子找供给刚性的卡口;给每个标的贴不可替代性标签(techmoat / capacitymoat / both / 待补)并列证据;含"卡口越硬越贵"与预期差四问的校准。当任务涉及产业链位置、上下游、护城河、不可替代性、供给瓶颈、竞争格局时加载;单纯取数、估值计算、财报拆分等不涉及产业链结构的任务不要加载。只产出框架与证据表,不给投资动作建议。.

simonlin1212/Vibe-Research · 212 tokens