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-judgmentnpx skills add monarchjuno/tradingcodex --skill tcx-judgmentgit 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-judgment)<a href="https://agentmods.dev/skills/monarchjuno/tradingcodex/tcx-judgment"><img src="https://agentmods.dev/badge/skills/monarchjuno/tradingcodex/tcx-judgment.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 | $0.00071 | $0.01014 |
| Opus 5 | $0.00036 | $0.00507 |
| Sonnet 5 | $0.00014 | $0.00203 |
| Haiku 4.5 | $0.00007 | $0.00101 |
Grade A, and why
tcx-judgment 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 4d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Judgment Review
Use this procedure when an accepted decision-oriented artifact needs independent challenge. Adjudicate the conclusion; do not merely accumulate objections or default to neutrality.
Treat the current user mandate, Investor Context, sealed Investment Brain, and sealed Strategy as the governing frame for this run:
- Brain supplies inquiry priorities, hypotheses, interpretation, and falsifiers.
- Strategy supplies applicable decision rules.
- Authenticated evidence controls whether their factual conditions hold.
- Judgment tests the evidence-to-interpretation-to-conclusion link.
You may overturn or qualify the current conclusion when that link fails under
the same frame. Never silently replace the mandate, Brain, or Strategy. If the
frame appears inapplicable or repeatedly defective, preserve that as a separate
frame concern for Head Manager or later postmortem; it does not amend the
current run.
Inputs:
- exact conflict or review question, the decision being adjudicated, and the downstream decision it can change
- a compact judgment frame containing the applicable mandate, Brain-derived questions or falsifiers, Strategy rules, and Investor Context constraints
- accepted, authenticated Artifact IDs with their service receipts/content hashes and handoff states; retrieve artifacts by exact ID
- source/as-of metadata, source trust notes, and forecast fields
- stated missing evidence, blocked actions, and downstream recipient
Treat paths and compact summaries as navigation aids, never substitutes for
authenticated IDs, receipts/hashes, or the exact conflict question. Return
waiting when a required accepted input or the conflict question is missing.
Choose the strongest task-relative countercase. Bull-versus-bear is useful for directional investment claims, but do not force it onto every request; use an appropriate alternative hypothesis, adverse scenario, assumption challenge, or claim-versus-refutation for the actual decision.
Make the following explicit in concise professional prose:
- adjudicated conclusion under the governing frame: maintain, change, qualify, or abstain
- material delta from the reviewed conclusion and the decisive reason
- strongest supporting evidence
- strongest contrary case and whether it survives
- weak, stale, missing, or discounted source posture
- overconfidence risk
- assumptions that would change the conclusion
- source trust notes
- update triggers
- invalidation conditions
- frame compliance and any separate frame concern
- owning role for any required revision
- review outcome:
accepted,revise,blocked, orwaiting
Evidence weighting:
- Require official source-of-record evidence when exact issuer, regulator, exchange, filing, contractual, or policy status is material.
- Treat management claims as source claims until independently supported.
- Treat market-derived evidence as useful but timestamp-sensitive.
- Treat attributable OpenBB/provider data, credible institutional data, and reputable secondary reporting as usable evidence for the claims and periods they competently cover. They may support a final conclusion without a primary duplicate when attribution, freshness, and coverage are adequate and no material conflict remains.
- Discount stale evidence, unsupported assumptions, and sources with missing as-of or retrieved-at posture.
Outcome rules:
- Use
acceptedwhen conclusion-driving claims have fit-for-purpose support and contrary evidence, source trust, update triggers, and invalidation conditions are explicit enough for downstream use. The adjudicated conclusion may maintain, change, qualify, or abstain;acceptedmeans the review itself is downstream-ready. Do not request revision solely because support is non-primary. - Use
revisewhen an owning role can fix weak evidence, missing source posture, unsupported assumptions, or unclear forecast/update fields. - Use
blockedwhen the conclusion depends on unavailable evidence, policy conflicts, missing profile context, or unsupported downstream authority. - Use
waitingwhen required upstream artifacts or accepted handoff state are missing.
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.
- 4d ago First seen · 107 lines · 71 tokens per session scan A 759b911bed68
tcx-judgment is a skill published in the GitHub repository monarchjuno/tradingcodex (366 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,014 once invoked, about $0.0004 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
consulting-analysis
Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis, industry research, competitive intelligence, investment due diligence, or any consulting-grade analytical report. This…
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。.
moai-foundation-core
Provides MoAI-ADK foundational principles including TRUST 5 quality framework, SPEC-First DDD methodology, delegation patterns, progressive disclosure, agent catalog reference, and token budget management (absorbed from moai-foundation-context). Use when referencing TRUST 5 gates, SPEC workflow, or context window…
moai-domain-html-report
Markdown-to-single-file-HTML report renderer. Six modes (status, incident, plan, explainer, financial, pr) selected by report type, crossed with three audience tiers (expert, basic, learn) derived from the active output style. The basic and learn tiers enrich the HTML with mermaid flowcharts, worked examples, and…