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 skills add vivy-yi/finance-skills --skill project-switchgit clone --depth 1 https://github.com/vivy-yi/finance-skillsWrote 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/skills/vivy-yi/finance-skills/project-switch)<a href="https://agentmods.dev/skills/vivy-yi/finance-skills/project-switch"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/project-switch/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vivy-yi/finance-skills/project-switch"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/project-switch.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00151 | $0.01681 |
| Opus 5 | $0.00076 | $0.00840 |
| Sonnet 5 | $0.00030 | $0.00336 |
| Haiku 4.5 | $0.00015 | $0.00168 |
Grade A, and why
project-switch 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 9d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
加载上下文
首次执行: 读取 ../references/项目空间结构.md 了解 project.md 字段规范。
本 skill 本身不读项目内容,只设置 current_project_code 上下文变量。后续 skill 通过此变量定位项目目录。
/finance:project-switch — 切换项目上下文
把当前会话的"项目上下文"切到指定项目。所有后续 skill 操作都基于该项目的 project.md 中的阈值/范围/历史上下文。
命令格式
/finance:project-switch <project-code> [--show]
参数:
<project-code>:项目代码(如2026-audit-ic/Q2-2026-budget/tax-filing-2026/m-and-a-deal-alpha)--show:只显示当前激活项目,不切换
操作步骤
步骤 1:定位项目目录
项目根目录 = ~/.config/finance-skills/projects/{project-code}/
如果目录不存在:
❌ 项目不存在: {project-code}
请使用 /finance:project-list 查看现有项目
或 /finance:project-new 创建新项目
步骤 2:校验 project.md
读取 {project-root}/project.md,校验:
- 必填字段齐全(项目类型/代码/负责人/周期/状态)
- YAML frontmatter 解析正确
状态字段是合法值(planning/active/fieldwork/reporting/closed)
如果 project.md 损坏或缺字段:
⚠️ project.md 损坏或缺必填字段
请运行 /finance:project-repair {project-code} 自动修复
或手动编辑 ~/.config/finance-skills/projects/{project-code}/project.md
步骤 3:检查项目状态
读取 状态 字段:
| 状态 | 是否允许切换 | 警告 |
|---|---|---|
planning |
✅ | "项目仍在规划阶段,未开始执行" |
active |
✅ | 无 |
fieldwork |
✅ | 无 |
reporting |
✅ | "项目在报告阶段,新发现可能不影响最终结论" |
closed |
⚠️ | "项目已关闭,切换为只读模式" |
archived |
❌ | "项目已归档,不可切换" |
closed 状态允许切换但提示只读。
步骤 4:写入会话上下文
将以下信息注入会话上下文:
current_project = {
code: "{project-code}",
type: "{project-type}",
root: "~/.config/finance-skills/projects/{project-code}/",
status: "{状态}",
started: "{开始日期}",
next_milestone: "{下次关键日期}",
}
关键约束:同时只能激活一个项目。如果已激活另一个项目:
⚠️ 当前已激活项目: {old-code}
切换到 {new-code} 将丢弃 {old-code} 的会话状态(包括未保存的临时笔记)
确认切换吗?[y/N]
步骤 5:输出切换结果
成功切换时输出:
════════════════════════════════════════
✅ 已切换到项目: {project-code}
项目类型: {type}
负责人: {name}
周期: {period}
当前阶段: {stage}
上次活动: {last-activity}
下次关键日期: {next-milestone}
════════════════════════════════════════
项目根目录: ~/.config/finance-skills/projects/{project-code}/
所有 skill 操作的产出物将记录到此项目。
输入 /finance:project-status 查看项目详情
输入 /finance:project-list 切换到其他项目
════════════════════════════════════════
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.
- 9d ago First seen · 176 lines · 151 tokens per session scan A 43f32a89eb7e
project-switch is a skill published in the GitHub repository vivy-yi/finance-skills (29 stars, last pushed 3mo ago), licensed MIT. It adds 151 tokens to every session and 1,681 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
hive.colony-progress-tracker
Claim tasks, record step progress, and verify SOP gates in the colony SQLite queue. Applies when your spawn message includes a dbpath field.
prd
A guide for writing a PRD, or Product Requirements Document, which explains what a product or feature should achieve and who it is for. It covers goals, users, success measures, limits, prior work, and excluded scope.
product-discovery
Product discovery workflow with OST, assumption testing, and interview scripts.
planning
A guide for planning software features and turning requests into clear requirements. It uses EARS, a plain format for stating what a system must do under specific conditions.
auto-status
A project dashboard skill that reports the current specification status for a project and its submodules. A specification is a written description of what should be built and how it should behave.
github-digest
You are a GitHub assistant generating a daily PR + issues digest for the user.