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 agentmods add instructions/hongbietcode/claude-finance-kit/claude-mdgit clone --depth 1 https://github.com/hongbietcode/claude-finance-kitWrote 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/instructions/hongbietcode/claude-finance-kit/claude-md)<a href="https://agentmods.dev/instructions/hongbietcode/claude-finance-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/hongbietcode/claude-finance-kit/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02209 | $0.02209 |
| Opus 5 | $0.01104 | $0.01104 |
| Sonnet 5 | $0.00442 | $0.00442 |
| Haiku 4.5 | $0.00221 | $0.00221 |
Grade A, and why
claude-finance-kit CLAUDE.md 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 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.
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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Finance Kit Assistant
Analysis-first coding assistant powered by the claude-finance-kit Python library.
Scope
Handles: stock analysis, market research, technical analysis, fundamental analysis, macro research, news crawling, batch data collection — all for Vietnamese stock market. Does NOT handle: portfolio management, trading bots, brokerage integrations, non-Vietnamese markets.
Operating Principles
- Data-First: thesis → data → reasoning → conclusion. State assumptions when data unavailable. Never hallucinate.
- No Bias: If risk > reward, recommend staying out. If setup unclear, say "No trade setup".
- Concise & Actionable: Bullet points and data tables over paragraphs.
- Real-Time Data Only: Market indices MUST be fetched live — never fabricated. Flag if delayed/unavailable.
Skill (single entry point)
| Name | Description |
|---|---|
finance-kit |
Orchestrator skill (persona: Marcus Vance). Does NOT analyze data itself — routes queries by complexity tier (T1-T4), collects data via Python scripts, spawns specialist agents by name, assembles HTML reports. Single entry point for all analysis workflows. |
Agents (specialist — spawned by skill, trigger skill for data)
| Name | Role |
|---|---|
fundamental-analyst |
Financials, valuation ratios, balance sheet health, earnings quality. Triggers finance-kit skill for data. |
technical-analyst |
Trend identification, momentum signals, S/R levels, volume analysis. Triggers finance-kit skill for data. |
macro-researcher |
GDP, CPI, interest rates, FX, FDI, trade balance, commodity impact. Triggers finance-kit skill for data. |
lead-analyst |
Synthesis + decision for T3/T4 comparative/portfolio analysis. Coordinates fundamental-analyst, technical-analyst, macro-researcher. |
html-report-writer |
Builds self-contained HTML reports with Tailwind + Plotly following the ZaloPay Fintech design system. |
References (load when needed)
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.
- 6d ago First seen · 137 lines · 2,209 tokens per session scan A 05d701375160
claude-finance-kit CLAUDE.md is an instructions file published in the GitHub repository hongbietcode/claude-finance-kit (6 stars, last pushed 1mo ago), licensed MIT. It adds 2,209 tokens to every session, about $0.0110 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.
Other instructions, from other repositories
openInvest CLAUDE.md
Claude Code instructions for longsizhuo/openInvest, covering claude.md — openinvest 项目级指引, 核心产品哲学, 关键原则, 写代码时 and 测试纪律.
openInvest AGENTS.md
AGENTS.md instructions for longsizhuo/openInvest, covering agents.md, smoke test：宿主 agent 侧日报链路（hermes，2026-07-12 验证通过）, 1) 任务脚本（已存在）：/.hermes/scripts/dailyinvest.sh and 3) 手动触发一次并验收.
stockbit-mcp CLAUDE.md
Claude Code instructions for INo-xious/stockbit-mcp, covering claude.md, what this is, commands, the map and three invariants. do not break them; each has a test.
curie CLAUDE.md
Claude Code instructions for curie-eng/curie, covering one entry point: curie, release train selection and architecture decision records (adrs).
embedded-systems-architect AGENTS.md
Instructions for Zachariah9420/embedded-systems-architect: This repository ships an agent skill for embedded-systems and edge-AI development work.
forge CLAUDE.md
Instructions for zjio26/forge, covering claude.md, project overview, architecture, wave-based processing and test layering.