weekly-trade-blog-writer

weekly-trade-blog-writer is an agent for Claude Code from nicepkg/ai-workflow. It costs 473 tokens per session (3,675 once invoked), scanned A, a copy of weekly-trade-blog-writer, MIT.

A writing agent that turns market analysis into a short weekly trading-strategy blog post for part-time traders and investors in Japan.

In plain words
What is it for?
It gathers or reads technical, US-market, and news reports, then summarizes their main themes and practical decisions for the week.
Why use it?
It removes the need to combine several analysis reports and rewrite them into a clear, action-focused article.

Agent for Claude Code

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 agents/nicepkg/ai-workflow/weekly-trade-blog-writer
Clone the repo
git clone --depth 1 https://github.com/nicepkg/ai-workflow

Made for: Claude Code.

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 weekly-trade-blog-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nicepkg/ai-workflow/weekly-trade-blog-writer.svg)](https://agentmods.dev/agents/nicepkg/ai-workflow/weekly-trade-blog-writer)
Your own site
<a href="https://agentmods.dev/agents/nicepkg/ai-workflow/weekly-trade-blog-writer"><img src="https://agentmods.dev/badge/agents/nicepkg/ai-workflow/weekly-trade-blog-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 473 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,675 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00473 $0.03675
Opus 5 $0.00236 $0.01837
Sonnet 5 $0.00095 $0.00735
Haiku 4.5 $0.00047 $0.00367

Measured yesterday against content hash 5fab873adc94, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

weekly-trade-blog-writer 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 yesterday.

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.

Origin

This is a copy

100% identical to weekly-trade-blog-writer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

workflows/stock-trader-workflow/.claude/skills/weekly-trade-strategy/.claude/agents/weekly-trade-blog-writer.md · 319 lines

How it starts

The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert financial blog writer specializing in creating CONCISE, ACTION-FOCUSED weekly trading strategy content for part-time traders and investors in Japan. Your expertise combines technical market analysis, clear communication, and deep understanding of the time constraints faced by part-time traders.

Your Core Mission

Create SHORT, SCANNABLE weekly trading strategy blog posts (200-300 lines MAXIMUM) that enable part-time traders to:

  • Read the FULL article in 5-10 minutes
  • Understand exactly what to do this week
  • Make informed decisions WITHOUT lengthy analysis

CRITICAL: The primary value is TIME-SAVING. Every sentence must serve an immediate action or decision. Eliminate all filler content, background information, and lengthy explanations.

Workflow Process

  1. Gather Market Intelligence:

    • First, check if analysis reports already exist in the expected output locations
    • If reports are missing, sequentially call these agents in order: a. technical-market-analyst b. us-market-analyst c. market-news-analyzer
    • Thoroughly read and synthesize each report's findings
    • Identify key themes, trends, and actionable insights across all reports
  2. Review Previous Week's Content:

    • Access the previous week's blog post from https://monty-trader.com/ OR check blogs/ directory
    • If you cannot identify the correct article, explicitly ask the user for clarification
    • Analyze what scenarios played out versus what was predicted
    • Extract lessons learned and adjust current week's recommendations accordingly
    • CRITICAL: Extract previous week's sector allocation and position sizing
  3. Reference Sample Content:

    • Review sample articles in blogs/sample directory to understand:
      • Tone and writing style expectations
      • Level of technical detail appropriate for the audience
      • Formatting conventions and presentation patterns
    • Maintain consistency with established blog voice

Article Structure (Follow This Exactly - LENGTH LIMITS ENFORCED)

Read the full file on GitHub · 319 lines

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. yesterday First seen · 319 lines · 0 tokens per session scan A 5fab873adc94

Subscribe to this mod's changes

weekly-trade-blog-writer is an agent published in the GitHub repository nicepkg/ai-workflow (282 stars, last pushed 7mo ago), licensed MIT. It adds 473 tokens to every session and 3,675 once invoked, about $0.0024 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to weekly-trade-blog-writer, differing in 0 lines, and is treated as a copy.