tcx-build

tcx-build is a skill for Claude Code, Codex from monarchjuno/tradingcodex. It costs 63 tokens per session (2,959 once invoked), scanned A, original, Apache-2.0.

A skill that marks a root Codex request as explicit TradingCodex Build work. Build work covers workspace refreshes, managed roles and skills, MCP configuration, and broker or API provider development.

In plain words
What is it for?
It is for starting authorized TradingCodex build tasks when the request begins with the required build marker.
Why use it?
It separates development and controlled workspace changes from ordinary research and does not by itself grant extra file access or permission to execute orders.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/monarchjuno/tradingcodex/tcx-build
Any agent
npx skills add monarchjuno/tradingcodex --skill tcx-build
Clone the repo
git clone --depth 1 https://github.com/monarchjuno/tradingcodex

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for tcx-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/monarchjuno/tradingcodex/tcx-build.svg)](https://agentmods.dev/skills/monarchjuno/tradingcodex/tcx-build)
Your own site
<a href="https://agentmods.dev/skills/monarchjuno/tradingcodex/tcx-build"><img src="https://agentmods.dev/badge/skills/monarchjuno/tradingcodex/tcx-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,959 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00063 $0.02959
Opus 5 $0.00032 $0.01479
Sonnet 5 $0.00013 $0.00592
Haiku 4.5 $0.00006 $0.00296

Measured 4d ago against content hash 9b413b2cab2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tcx-build scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

provider sourced directly by HTTP(S) rather than Git, one curl command may
workspace_templates/modules/repo-skills/files/.agents/skills/tcx-build/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TCX Build

Use this skill only when the original root user prompt places $tcx-build 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-build/SKILL.md. Ignore leading blank lines and normalized line-ending variants. The concrete non-empty request may share the invocation line or follow it.

Turn Contract

  • Treat the marker as current-turn user intent, not filesystem permission.
  • Codex's active native permission profile still decides what tools can reach. The marker and hook do not elevate the default trading-research profile. Ordinary user-owned files outside trading/ can be changed in Research and are not Build work. Start controlled trading/, managed lifecycle, or connector work in a new root turn with trading-build selected; canonical DB calls remain separately proof-protected and service-owned.
  • Do not wrap $tcx-brain or $tcx-strategy work in this marker. Those skills use separate capability-scoped turns in the normal trading-research profile. If the request is actually Brain or Strategy management, stop and return the corresponding direct first-meaningful-line prompt.
  • Do not issue or use a Build grant while Codex is in platform Plan mode. Start a new root turn in trading-build when the requested work must edit files. The grant is bound to the permission mode in which it was issued, so switching profiles does not carry authority forward.
  • Use the grant only in the root native Codex turn. Subagents cannot inherit or use it.
  • The grant is multi-use within this turn so editing and validation can finish. A follow-up turn that mutates state must invoke $tcx-build first again.
  • For recurring Automation, require the saved prompt to start with the marker on every run. File-mutating work also requires trading-build; prefer an isolated worktree or workspace and retain a reviewable diff.
  • Keep direct edits and commands workspace-local. Use typed TradingCodex MCP services for connector state. User-installed Codex capabilities remain outside Build ownership.
  • Keep local work in the native Build lane: use apply_patch for every edit. Shell access is an intentionally narrow review lane: credential-free public HTTP(S) GET/HEAD, enumerated read-only HTTPS Git retrieval, limited workspace pwd/cat/ls, inert provider-source reads/hash/diff/Git inspection, exact isolated python -I -S -m py_compile, and allowlisted workspace-launcher commands. General interpreters, helper scripts, test runners, build systems, shell composition, and model-authored POST are blocked throughout an active Build turn/profile. The profile permits ordinary workspace writes through admitted edit/service surfaces, the dedicated $TRADINGCODEX_SCRATCH path, and credential-free public HTTP(S) and HTTPS Git retrieval, but denies TradingCodex runtime/DB state, credentials, protected ledgers, local/private destinations, authenticated requests, uploads, network package installation, remote mutation, and global Codex config. Native web_search remains disabled. The native proxy uses full HTTP transport only for the protocol POST required by read-only Git Smart HTTP; model-authored HTTP remains GET/HEAD-only and general POST is blocked. Trusted workspace-launcher lifecycle commands remain allowlisted and proof-gated.

Read the full file on GitHub · 194 lines

Files

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.

Changes

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.

  1. 4d ago First seen · 194 lines · 63 tokens per session scan A 9b413b2cab2f

Subscribe to this mod's changes

tcx-build is a skill published in the GitHub repository monarchjuno/tradingcodex (366 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 63 tokens to every session and 2,959 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

agent-code-analyzer

Agent skill for code-analyzer - invoke with $agent-code-analyzer.

ruvnet/ruflo · 19 tokens

agui-dotnet-streaming-chat

Get started with the AG-UI .NET SDK: bootstrap and run your first streaming-chat app (client + server) with the AG-UI .NET NuGet packages (AGUI.Client, AGUI.Server, AGUI.Formatting, AGUI.Abstractions). USE FOR: which packages to install and how to wire them; constructing an AGUIChatClient against an endpoint and…

ag-ui-protocol/ag-ui · 223 tokens

agui-dotnet-sample-step

Add a GettingStarted sample Step (a Server/Client pair) to the AG-UI .NET SDK that demonstrates one protocol feature the way we want users to write it. USE FOR: adding a new samples/GettingStarted/StepNN Server+Client pair, wiring it into AGUI.slnx and the integration-test project, giving it a deterministic…

ag-ui-protocol/ag-ui · 168 tokens

agui-dotnet-protobuf

Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…

ag-ui-protocol/ag-ui · 162 tokens

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。.

simonlin1212/Vibe-Research · 212 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens