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/monarchjuno/tradingcodex/tcx-portfolionpx skills add monarchjuno/tradingcodex --skill tcx-portfoliogit clone --depth 1 https://github.com/monarchjuno/tradingcodexWrote 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/monarchjuno/tradingcodex/tcx-portfolio)<a href="https://agentmods.dev/skills/monarchjuno/tradingcodex/tcx-portfolio"><img src="https://agentmods.dev/badge/skills/monarchjuno/tradingcodex/tcx-portfolio.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 5.1 | $0.00033 | $0.00589 |
| Opus 5 | $0.00016 | $0.00295 |
| Sonnet 5 | $0.00007 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
tcx-portfolio 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 6d 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.
What it actually says
Portfolio Review
Use this skill to evaluate portfolio fit before an order ticket is drafted or before an investment view is escalated into risk/sizing work.
Codex-native state access:
- Prefer TradingCodex MCP read/status tools such as
list_broker_connections,get_portfolio_snapshot, andlist_reconciliation_runsover manually reconstructing portfolio state from chat context. - Use
sync_broker_accountonly when the user or workflow asks for a fresh read-only sync and the broker connection is already reviewed for read scope. - Treat reconciliation warnings or stale sync state as readiness constraints, not as data to smooth over.
Universe method:
- Identify asset universe, instrument, account/context, benchmark, existing exposure, and whether the installed harness supports the instrument.
- Public equity and ETF/index reviews should consider active weight, sector/factor exposure, liquidity, concentration, benchmark comparison, rolling contribution, timing attribution, and opportunity cost when data exists.
- Use Brinson-style allocation/selection language, factor attribution, or timing attribution only when holdings, benchmark, and return data are explicit; otherwise name the missing inputs.
- Crypto, macro, FX, rates, commodities, options, and credit-linked exposures require instrument-specific implementation inputs; mark missing support as
not-decision-readyrather than sizing from thin context. - Separate portfolio fit from personal investment advice.
Expected output:
- Universe, instrument, and portfolio context
- Existing exposure
- Position size context
- Concentration risk
- Liquidity and holding period fit
- Opportunity cost
- Performance attribution or benchmark-relative contribution when supportable
- Portfolio recommendation
- Draft readiness: ready, revise, or no-order
- Source/as-of posture and missing implementation inputs
Decision quality fields when applicable:
evidence_grade,source_freshness,source_qualitydecision_quality_required,decision_readiness,confidenceinvestor_context_gate_required,investor_context_gapsforecast_required,forecast_allowed,forecast_block_reasoncontrary_evidence,update_triggers,invalidation_conditions
Role-specific quality:
- Tie sizing and fit to the user's stated portfolio context.
- Name concentration, correlation, liquidity, and opportunity-cost assumptions.
- State the binding constraint and whether the output is
screen-grade,ready-for-portfolio-risk,ready-for-draft, ornot-decision-ready. - Do not fabricate positions, cash, costs, capacity, or user constraints.
- State whether the next step is review-only, ready for risk review, or ready for draft.
Write outputs under trading/reports/portfolio/.
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.
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.
- 6d ago First seen · 58 lines · 33 tokens per session scan A 51d1b9968575
tcx-portfolio is a skill published in the GitHub repository monarchjuno/tradingcodex (366 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 589 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.
Other skills, from other repositories
agent-trading-predictor
Agent skill for trading-predictor - invoke with $agent-trading-predictor.
agent-agentic-payments
Agent skill for agentic-payments - invoke with $agent-agentic-payments.
agent-payments
Agent skill for payments - invoke with $agent-payments.
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。.
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。.
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。.