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-evidencenpx skills add monarchjuno/tradingcodex --skill tcx-evidencegit 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-evidence)<a href="https://agentmods.dev/skills/monarchjuno/tradingcodex/tcx-evidence"><img src="https://agentmods.dev/badge/skills/monarchjuno/tradingcodex/tcx-evidence.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 | $0.00038 | $0.00870 |
| Opus 5 | $0.00019 | $0.00435 |
| Sonnet 5 | $0.00008 | $0.00174 |
| Haiku 4.5 | $0.00004 | $0.00087 |
Grade A, and why
tcx-evidence 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Collect Evidence
Build the smallest evidence set that can answer the assigned question.
Choose one artifact by default
- Create an
evidence_packundertrading/research/only when source intake has independent reuse or cross-role handoff value, or preserves a material source conflict or gap separately from a role conclusion. - Create a
role_reportundertrading/reports/<role>/when the output includes that role's analysis, conclusion, or downstream handoff. When collected evidence only supports that same report, create the role report directly; an evidence pack is not a prerequisite or default duplicate. - When both are justified, create the evidence pack first. Put its authenticated
Artifact ID in the role report's
input_artifact_ids, retain every exact Snapshot/Dataset ID the report uses, and rely on service receipts/hashes for lineage. Do not copy the same body into both artifacts. - When persistence has no reuse, provenance, decision, or audit value, hand off compact IDs without creating either artifact.
- Identify the universe and workflow type. Use only relevant, callable source classes; mark missing universe support or unavailable routes as gaps.
- Apply
tcx-source-gatebefore external retrieval and retain its returned source IDs and gaps. If analysis exposes a material gap, conflict, stale anchor, or identifier mismatch within your assigned question and specialty, collect the additional evidence needed to resolve it without waiting for a new field-by-field instruction. Use evidence value, not a fixed source or call count, as the stopping rule. - Distinguish observations, source or management claims, analysis, and assumptions in natural prose where ambiguity matters. Use opened filings, releases, and exchange/regulator records when source-of-record status matters. Otherwise accept attributable OpenBB/provider data, credible institutional data, and reputable secondary reporting for the claims they competently and currently cover. A search snippet or unsupported assumption is not evidence.
- State the identifier, source list, source-trust notes, market context, missing evidence, freshness, decision readiness, confidence, update triggers, invalidation conditions, and contrary evidence that matter.
- If persisting, apply
$tcx-artifact, the canonical shared quality floor, and use authenticated MCP.
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 · 69 lines · 38 tokens per session scan A e6464679e635
tcx-evidence 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 870 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。.