Borrowing it
Nothing to install: this file belongs to Eric-KY-Zhang/FinPrism. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Eric-KY-Zhang/FinPrism/main/CLAUDE.mdgit clone --depth 1 https://github.com/Eric-KY-Zhang/FinPrismWrote 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/eric-ky-zhang/finprism/claude-md)<a href="https://agentmods.dev/instructions/eric-ky-zhang/finprism/claude-md"><img src="https://agentmods.dev/badge/instructions/eric-ky-zhang/finprism/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 | $0.06031 | $0.06031 |
| Opus 5 | $0.03016 | $0.03016 |
| Sonnet 5 | $0.01206 | $0.01206 |
| Haiku 4.5 | $0.00603 | $0.00603 |
Grade A, and why
FinPrism 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 8d 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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — FinPrism 项目专属操作手册
本文件是
AGENTS.md的配套实施细节，存放本项目专属的规则、不变量、命令、目录导航等"具体到 FinPrism 才适用"的内容。同步规则：每次修改 AGENTS.md 时，必须检视本文件相应章节是否需要联动更新。AGENTS.md 偏原则（少变），CLAUDE.md 偏现状（常变，跟着 phase / release 走）。
当前对应版本：v1.2（Sprint 5 收口，归档维护） + v2 Week 0 scaffolding 完成（参见
docs/adr/0001-v2-pivot-from-vba-to-exe.md与docs/plans/V2_ROADMAP.md）
0. v1.2 vs v2 现状速读
| 维度 | v1.2 (current shipped) | v2 (planning / building) |
|---|---|---|
| 形态 | Excel xlsm + VBA macro | PyInstaller EXE + Tkinter GUI，无 macro |
| 状态 | shipped，仍是用户唯一可用版本 | Week 0 scaffolding 完成，未发布 |
| 仓库位置 | v1_vba/ |
v2_python/ |
| 接什么 PR | 只接 safety fix；不接新功能 | 全部新开发 |
| 决策依据 | v1_vba/STATUS.md §HH |
docs/adr/0001-v2-pivot-from-vba-to-exe.md |
| 上线后命运 | 归档维护，只接 safety fix | 取代 v1.2，成为唯一活跃版本 |
Agent 进项目第一动作判断分支：
- 用户提的需求是修 v1.2 bug / 优化 / 用户使用问题 → 走 §1-§8 v1.2 规则
- 用户提的是 v2 实施 / 框架抽取 / golden diff → 走 ADR-0001 + V2_ROADMAP.md
- 不确定的时候停下问，不要把 v1.2 的逻辑塞到 v2 里
1. 项目快速导航
| 入口 | 用途 | 何时读 |
|---|---|---|
README.md |
用户使用说明 + 当前版本概览 + 更新日志 | 第一次接触项目 / 解释给用户 |
v1_vba/STATUS.md |
v1.2 完整开发记录与各 phase 状态收口 | 找 v1.2 历史决策 / 看最新基线（看末尾 §HH） |
v1_vba/ARCHITECTURE.md |
v1.2 模块依赖、sheet inventory、数据流、invariants | 写 v1.2 safety fix 前 / 改 v1.2 架构相关时 |
v1_vba/RISK_REGISTER.md |
v1.2 风险登记表（数据准确性 / 部署 / 代码质量 / 文档） | 评估 v1.2 变更影响时 |
AGENTS.md |
Agent 协作通用原则 | 第一次进入项目 |
CLAUDE.md |
本文件，项目专属细则 | 落地任何操作前 |
docs/PROJECT_RETROSPECTIVE.md |
项目复盘（v1.0 + v1.1 + v1.2 三轮 postscript） | 想了解项目演化历程时 |
docs/PHASE5A_CHANGELOG.md |
Phase 5a 雪球 cookie 自动化事实记录 | 排查 XueqiuHttpGet / FetchViaPowerShell 相关问题 |
docs/sprint5_conflicts.md |
v1.2 Sprint 5 Public 符号冲突扫描记录 | 拆分 / 新增子模块前 |
docs/CODEX_HANDOFF_PHASE_5A_PUSH.md |
Phase 5a handoff（含跨 phase snapshot） | Codex / Reviewer 交接 |
docs/plans/CODEX_HANDOFF_PHASE_4F.md |
Phase 4-5 过渡 handoff | Phase 4f 细节 |
docs/deep-research-report.md |
外部 deep research 评估 (背景材料；多处与最终决策分歧，见 ADR-0001) | 评估 v2 历史选择时参考 |
docs/adr/0001-v2-pivot-from-vba-to-exe.md |
v2 主决策 ADR：14 个根决策、备选拒绝原因、反向触发条件 | 任何涉及 v2 架构 / scope 的工作前必读 |
docs/plans/V2_ROADMAP.md |
v2 实施路线图：Week 0 - Week 11+ 节奏、每段交付物、严禁动 | v2 开发期 agent 进项目首读 |
v2_python/README.md |
v2 Python 开发入口、命令和当前阶段说明 | v2 代码开发 / 本地验证 |
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.
- 8d ago First seen · 327 lines · 6,031 tokens per session scan A d2c551d5c268
FinPrism CLAUDE.md is an instructions file published in the GitHub repository Eric-KY-Zhang/FinPrism (5 stars, last pushed 3mo ago), licensed MIT. It adds 6,031 tokens to every session, about $0.0302 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.