tcx-automate

tcx-automate is a skill for Claude Code, Codex from monarchjuno/tradingcodex. It costs 78 tokens per session (2,458 once invoked), scanned B, original, Apache-2.0.

A skill for creating or updating scheduled tasks in the Codex app. A scheduled task runs a saved request at recurring times.

In plain words
What is it for?
It is for setting the schedule, workspace, request, output, notifications, stopping conditions, and allowed effect level for recurring work.
Why use it?
It removes the need to manually repeat monitoring, research, portfolio reviews, order preparation, or other recurring TradingCodex work.

Skill for Claude CodeCodex

Written for Claude Code and Codex: UserPromptSubmit hook event, but also agents/openai.yaml present. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions Codex.

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-automate
Any agent
npx skills add monarchjuno/tradingcodex --skill tcx-automate
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-automate

README.md
[![agentmods](https://agentmods.dev/badge/skills/monarchjuno/tradingcodex/tcx-automate.svg)](https://agentmods.dev/skills/monarchjuno/tradingcodex/tcx-automate)
Your own site
<a href="https://agentmods.dev/skills/monarchjuno/tradingcodex/tcx-automate"><img src="https://agentmods.dev/badge/skills/monarchjuno/tradingcodex/tcx-automate.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,458 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 5.1 $0.00078 $0.02458
Opus 5 $0.00039 $0.01229
Sonnet 5 $0.00016 $0.00492
Haiku 4.5 $0.00008 $0.00246

Measured 6d ago against content hash d32eb49dcad7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

tcx-automate scanned grade B 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 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

7. Write the registration summary and future-run output instructions in the
workspace_templates/modules/repo-skills/files/.agents/skills/tcx-automate/SKILL.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Automate Workflow

Create or update a Codex app Automation. This skill authors the scheduled task; it is not the prompt that a scheduled run should invoke.

Procedure

  1. Capture the schedule, attached workspace, recurring request, desired output, and stop or notification conditions. Ask only for fields that materially affect the requested task.
  2. Use $tcx-plan only when ambiguity would change scope, schedule, allowed actions, approval posture, or a stop condition. Register a clear research or monitoring request without forcing a planning interview.
  3. Select the skill the future run should actually use, such as $tcx-workflow, $tcx-memory, or $tcx-server. Do not put $tcx-automate in the saved runtime prompt; that would recursively ask each run to create another automation.
  4. Choose the narrowest effect level explicitly requested:
    • report-only: research, monitoring, recurring analysis, portfolio review, or status reporting; this is the default.
    • draft-order: may prepare a canonical draft order but cannot approve or submit it.
    • assisted-execution: may prepare approval and execution-ready context, then report the exact manual action required from the user.
    • turn-authorized-execution: may submit only when the saved prompt starts with the canonical plain $tcx-order-allow invocation described below.
    • turn-authorized-build: may perform workspace-local mutations only when the saved prompt starts with the canonical plain $tcx-build invocation described below. A task that changes workspace files must run with workspace-write; read-only cannot gain file-write authority, while Plan cannot issue or use the Build grant at all. Treat this as recurring delegated write intent, never as permission elevation.
    • capability-scoped-management: may manage exactly one Investment Brain or Strategy only when the saved prompt starts with $tcx-brain or $tcx-strategy. It runs in trading-research and cannot cross into Build, another managed capability, or order execution.
  5. Build a compact saved prompt containing the selected runtime skill, the original recurring request and constraints, current-data or as-of rules, expected output, and explicit blocked actions. Let Head Manager choose or revise exact roles from each run's current evidence; never store a role roster, lane, or DAG.
  6. Reuse a matching Codex app Scheduled Task when possible. If the Automation control is unavailable, return the schedule and ready-to-register prompt instead of creating scheduler code or raw task files.
  7. Write the registration summary and future-run output instructions in the user's language unless the user asks for another language.

Read the full file on GitHub · 232 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. 6d ago First seen · 232 lines · 78 tokens per session scan B d32eb49dcad7

Subscribe to this mod's changes

tcx-automate is a skill published in the GitHub repository monarchjuno/tradingcodex (366 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 78 tokens to every session and 2,458 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.