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 skills add monarchjuno/tradingcodex --skill tcx-strategygit 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-strategy)<a href="https://agentmods.dev/skills/monarchjuno/tradingcodex/tcx-strategy"><img src="https://agentmods.dev/badge/skills/monarchjuno/tradingcodex/tcx-strategy/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/monarchjuno/tradingcodex/tcx-strategy"><img src="https://agentmods.dev/badge/skills/monarchjuno/tradingcodex/tcx-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 10 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
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 | $0.00079 | $0.02105 |
| Opus 5.5 | $0.00032 | $0.00842 |
| Sonnet 5.5 | $0.00016 | $0.00421 |
| Haiku 4.5 | $0.00008 | $0.00211 |
Grade A, and why
tcx-strategy 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 1mo 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strategy Creator
Use this skill to author and manage strategy skills. A strategy skill is a standalone Codex-compatible skill whose name starts with strategy-, stored as a normal project skill under .agents/skills/strategy-*. It captures a user-approved investment strategy as an agent-readable operating procedure and should remain usable without importing TradingCodex service code.
Strategy skills guide judgment only. They never approve orders, execute orders, override policy, change MCP allowlists, bypass role boundaries, read secrets, or grant broker authority.
Each workflow must bind the selected strategy name and content hash before analysis. Later edits do not rewrite the strategy snapshot used by an earlier decision, replay, forecast, or postmortem. Historical and forward evidence may justify a draft change proposal, but it never silently changes or activates the strategy.
In native Codex, selection requires one exact explicit $strategy-* id, either
as a plain invocation or a Markdown link whose label and target match the
projected workspace skill. Repeated references to the same id are deduplicated;
distinct multiple ids fail closed. An unprefixed name or natural-language
similarity never selects a strategy. The hook accepts only an active validated
workspace strategy and seals its content under the run before planning. The
read-only viewer never selects a strategy.
The generated strategy body must be standalone. Do not mention platform names, platform role identifiers, subagent mechanics, MCP, approval gates, execution gates, or handoff mechanics inside the strategy skill. If a section has no user-provided rule, write not specified without adding a delegation sentence.
Managed Turn Admission
Creating, updating, activating, archiving, or deleting a strategy is a durable
managed operation. Proceed only when the current root prompt has
$tcx-strategy on its first meaningful line. Accept the plain token or a
Markdown skill link only when its label and target match this workspace's
projected tcx-strategy/SKILL.md; the concrete non-empty request may share the
line or follow it. Do not combine it with $tcx-build, $tcx-brain, or an
order marker. Use the
normal trading-research profile; the marker admits only allowlisted Strategy
lifecycle calls through the proof-protected manage_strategy MCP tool for this
root turn. It does not grant generic Build, Brain,
order, credential, publication, or global-config authority. Plan mode and
subagents cannot issue or use the grant.
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.
- 1mo ago First seen · 203 lines · 79 tokens per session scan A ac29c2b8bd00
tcx-strategy is a skill published in the GitHub repository monarchjuno/tradingcodex (376 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 2,105 once invoked, about $0.0003 per session on Opus 5.5. 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.
serenity-skill
Research technology and advanced-manufacturing investments using Serenity-inspired supply-chain bottleneck analysis. Use for theme scans, company thesis challenges, candidate comparisons, or learning this method. Prioritize A-shares unless another market is requested. Return research priorities, dated evidence, profit…
daily-deep-brief
A scheduled, pre-market investment briefing for Hong Kong and United States stocks. A deterministic preparation step gathers data and an agent adds judgment, while a later step validates and publishes the result.
imf-data
Retrieve and analyze IMF macroeconomic series, forecasts, and reserve-composition data.