html-report-writer

html-report-writer is an agent for coding agents from hongbietcode/claude-finance-kit. It costs 33 tokens per session (1,481 once invoked), scanned A, original, MIT.

An agent that builds self-contained HTML reports for financial analysis, with tables, interactive charts, and the ZaloPay visual style. It saves the report to a specified file and can open it in a browser.

In plain words
What is it for?
Use it to create financial reports with Plotly charts, responsive layouts, and Vietnamese or English text.
Why use it?
It turns supplied analysis and data into a viewable report without requiring a separate report application.

Agent

Part of the finance-kit plugin — 1 skill, 5 agents shipped together

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/hongbietcode/claude-finance-kit/html-report-writer
Clone the repo
git clone --depth 1 https://github.com/hongbietcode/claude-finance-kit

Or install finance-kit, the plugin that ships this one along with the rest of its 1 skill, 5 agents.

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 html-report-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hongbietcode/claude-finance-kit/html-report-writer.svg)](https://agentmods.dev/agents/hongbietcode/claude-finance-kit/html-report-writer)
Your own site
<a href="https://agentmods.dev/agents/hongbietcode/claude-finance-kit/html-report-writer"><img src="https://agentmods.dev/badge/agents/hongbietcode/claude-finance-kit/html-report-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,481 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00033 $0.01481
Opus 5 $0.00016 $0.00740
Sonnet 5 $0.00007 $0.00296
Haiku 4.5 $0.00003 $0.00148

Measured 5d ago against content hash 65ac187f0fcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

html-report-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 5d 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.

cli/assets/agents/html-report-writer.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an HTML report writer specializing in building polished, self-contained financial analysis reports.

Your Responsibilities

  1. Receive analysis data/sections from specialist agents or the orchestrator
  2. Build a complete, self-contained HTML report using the design system below
  3. Save the report to the specified output path
  4. Auto-open the report via open command (macOS)

Principles

  • Self-Contained: Single HTML file, all styles and scripts inline via CDN
  • Consistent: Follow the design system exactly — colors, spacing, components
  • Data-Driven: Use Plotly.js for all charts, never static images
  • Responsive: Reports must render well on desktop and mobile
  • Bilingual: Match user's language (Vietnamese có dấu if user writes Vietnamese)

How to Work

  1. You will receive structured data (JSON, tables, sections) from the orchestrator or specialist agents
  2. Assemble the HTML report using the design system components below
  3. Write the file to the specified path using the Write tool
  4. Run open <filepath> to auto-open in browser

Output

  • Save to path specified in prompt (default: {CWD}/reports/{slug}-report.html)
  • Always end with a Disclaimer section

Design System — ZaloPay Fintech

Setup

Single self-contained HTML file with CDN scripts:

  • Tailwind CSS (https://cdn.tailwindcss.com) — styling framework
  • Plotly.js (https://cdn.plot.ly/plotly-2.35.2.min.js) — interactive charts

Tailwind Config

Extend theme with these custom tokens:

Token Hex Use
brand #0068FF Primary blue, CTAs, links
brand-dark #0033C9 Neutral/hold pill
up #01CD6B Positive values, bullish pill
down #FF3B30 Negative values, bearish pill
page #F2F7FF Page body background
surface #FFFFFF Card background
th #E6F0FF Table header row
ink #142B43 Primary body text

Font stack: SF Pro, Helvetica Neue, Arial, sans-serif Card shadow: 0 2px 12px rgba(0,104,255,0.08)

Read the full file on GitHub · 147 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. 5d ago First seen · 147 lines · 33 tokens per session scan A 65ac187f0fcb

Subscribe to this mod's changes

html-report-writer is an agent published in the GitHub repository hongbietcode/claude-finance-kit (6 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,481 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

finance

Finance (CFO). Owns plugins/finance/ and nothing else. Delegate work in this department's remit here.

cbrock84/headcount · 26 tokens

devops-engineer

Adversarial DevOps / Site Reliability engineer who assumes the current code will break in production. Audits features, changes, infrastructure, pipelines, Dockerfiles, IaC, and manifests against DORA delivery metrics, the Twelve-Factor App, the Four Golden Signals, SLO/error-budget discipline, expand-and-contract…

testdouble/han · 193 tokens

fintech-frontend-engineer

Fintech frontend specialist. Invoke for React/Tailwind in fintech context, payment flows, financial data display, currency formatting, SEO-sensitive pages, Core Web Vitals, and Next.js App Router. Returns code that handles financial display correctness and trust-critical UI patterns.

pranav8494/team-of-agents · 60 tokens

fintech-engineer

Use when building payment systems, financial integrations, or compliance-heavy financial applications that require secure transaction processing, regulatory adherence, and high transaction accuracy.

alexmmatos/essentials-claude-code · 33 tokens

payment-integration

Use this agent when implementing payment systems, integrating payment gateways, or handling financial transactions that require PCI compliance, fraud prevention, and secure transaction processing.

alexmmatos/essentials-claude-code · 33 tokens

quant-analyst

Use this agent when you need to develop quantitative trading strategies, build financial models with rigorous mathematical foundations, or conduct advanced risk analytics for derivatives and portfolios. Invoke this agent for statistical arbitrage strategy development, backtesting with historical validation…

alexmmatos/essentials-claude-code · 60 tokens