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-fundamentalnpx skills add monarchjuno/tradingcodex --skill tcx-fundamentalgit 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-fundamental)<a href="https://agentmods.dev/skills/monarchjuno/tradingcodex/tcx-fundamental"><img src="https://agentmods.dev/badge/skills/monarchjuno/tradingcodex/tcx-fundamental.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 | $0.00644 |
| Opus 5 | $0.00016 | $0.00322 |
| Sonnet 5 | $0.00007 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
tcx-fundamental 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
Fundamental Analysis
Use this skill for business, accounting, financial statement, issuer, protocol/project, sector, and fundamental quality analysis when the installed workflow can support the requested universe.
Universe method:
- Public equity: analyze business model, financial statement linkage, earnings quality, cash conversion, DuPont-style driver decomposition when useful, management, capital allocation, operating KPIs, source/as-of posture, and evidence gaps.
- ETF/index: analyze constituent, sector, factor, liquidity, passive-flow, and methodology fundamentals only when supported by evidence.
- Crypto public markets: analyze protocol economics, supply, usage, governance, liquidity, and ecosystem fundamentals as research context only.
- Macro/rates/FX/commodities: identify the relevant fundamental transmission channel and call out specialist underwriting gaps rather than inventing unsupported coverage.
- Credit signals may inform common-equity or portfolio downside; do not underwrite debt securities unless a dedicated credit workflow is installed.
Expected output:
- Universe and workflow type
- Business model
- Revenue and margin drivers
- Balance sheet and cash flow quality
- Earnings-quality, cash-conversion, statement-linkage, and red-flag notes
- Management and capital allocation
- Fundamental risks
- Evidence and source notes
- Source/as-of posture, stale data, and missing support gaps
Decision quality fields when applicable:
evidence_grade,source_freshness,source_qualityscenario_cases,contrary_evidence,update_triggersinvalidation_conditions,decision_readiness,confidence- forecast permission fields when prediction or decision support is in scope
Role-specific quality:
- State what matters most for the company instead of listing generic ratios.
- Explain drivers, risks, and uncertainty in plain causal terms.
- Reconcile filing-derived aggregates to the underlying filing or disclosure: identifier/accession, accepted or published time, form, fiscal period, units, and amendment posture. For a historical cutoff, use only the version available then; a latest company-facts view cannot silently replace it.
- Distinguish issuer/company fundamentals from security actionability; good fundamentals alone are not a buy decision.
- Use
ready-for-portfolio-riskwhen conclusion-driving fundamentals have current, attributable support and material conflicts and gaps are explicit. Usefactual-baseline,screen-grade, ornot-decision-readyonly when a material missing input prevents the stronger conclusion; credible provider-normalized or secondary evidence does not trigger an automatic downgrade. - Do not fabricate financial metrics, source facts, filings, or validation results.
- Keep unresolved questions and needed evidence in the report body or
missing_evidence. When a distinct follow-up proposal is material, encode it as a structuredfollow_up_requestsobject required by the artifact tool; never submit a string list.
Write outputs under trading/reports/fundamental/.
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 · 60 lines · 33 tokens per session scan A f8885ea94f50
tcx-fundamental 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 644 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。.