approval-matrix

approval-matrix is a skill for Claude Code from vivy-yi/finance-skills. It costs 93 tokens per session (2,196 once invoked), scanned A, original, MIT.

A framework for defining who can approve different business or financial actions, including approval levels, amount limits, and exceptions.

In plain words
What is it for?
Use it when setting up or revising approval rules for expenses, purchases, contracts, assets, hiring, marketing, investments, and other decisions.
Why use it?
It reduces uncertainty and control risk by making approval authority explicit and separating requesting, approving, executing, and recording duties.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions CLAUDE.md.

Good fit Use it when setting up or revising approval rules for expenses, purchases, contracts, assets, hiring, marketing, investments, and other decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vivy-yi/finance-skills/approval-matrix
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.

Any agent
npx skills add vivy-yi/finance-skills --skill approval-matrix
Clone the repo
git clone --depth 1 https://github.com/vivy-yi/finance-skills

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 approval-matrix

README.md
[![agentmods](https://agentmods.dev/badge/skills/vivy-yi/finance-skills/approval-matrix/github.svg)](https://agentmods.dev/skills/vivy-yi/finance-skills/approval-matrix)
Your own site
<a href="https://agentmods.dev/skills/vivy-yi/finance-skills/approval-matrix"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/approval-matrix/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.

agentmods 80×15 button for approval-matrix

Your own site · 80×15
<a href="https://agentmods.dev/skills/vivy-yi/finance-skills/approval-matrix"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/approval-matrix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,196 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00093 $0.02196
Opus 5 $0.00046 $0.01098
Sonnet 5 $0.00019 $0.00439
Haiku 4.5 $0.00009 $0.00220

Measured 9d ago against content hash 0f56131403b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

approval-matrix 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.

finance-skills/skills/internal-control/skills/approval-matrix/SKILL.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

加载上下文

首次使用时: 读取 ../../CLAUDE.md 获取场景级配置(公司组织架构/审批层级定义/例外审批规则)。


/approval-matrix — 审批权限矩阵

Examples

→ 示例:用户说"采购超过 50 万的审批权限现在都在总监,要不要改成分级审批",系统应调用本技能,生成新的分级审批矩阵建议。

→ 示例:用户说"新业务线的费用审批没有规定,帮我设计一套适合他们的审批矩阵",系统应调用本技能,根据业务特征设计审批矩阵。

→ 示例:用户说"审计发现付款审批只有一级,帮我评估风险并给出优化建议",系统应调用本技能,评估现状并输出优化方案。

审批矩阵设计原则

分层授权原则:
  → 金额越大,审批层级越高
  → 风险越高,审批要求越严格
  → 业务越特殊,例外条款越多

不相容职务分离:
  → 申请与审批分离
  → 审批与执行分离
  → 执行与记录分离

第一步:梳理审批场景

主要财务审批场景:

□ 费用报销:[单笔/累计]
□ 采购付款:[订单/预付款/尾款]
□ 合同签署:[金额区间]
□ 借款/担保:[内部/外部]
□ 资产购置:[单项限额]
□ 人员招聘:[薪资范围]
□ 差旅标准:[住宿/交通/补贴]
□ 营销费用:[单项活动]
□ 投资决策:[金额区间]

各场景风险特征:

| 场景 | 频率 | 风险等级 | 特殊要求 |
|------|------|---------|---------|
| 费用报销 | 高 | [中] | [无] |
| 采购付款 | 中 | [高] | [需两家比价] |
| 合同签署 | 低 | [高] | [法务审核] |

第二步:设计分层授权体系

标准分层(示例,可按实际调整):

层级  | 角色           | 审批限额(单项)
------|----------------|----------------
L1    | 专员/主管      | ≤ [X] 万
L2    | 经理           | ≤ [X] 万
L3    | 总监           | ≤ [X] 万
L4    | 副总裁/VP      | ≤ [X] 万
L5    | CFO            | ≤ [X] 万
L6    | CEO            | ≤ [X] 万
L7    | 董事会          | > [X] 万

按场景的金额阈值:

□ 费用报销:
  → 主管:[X] 万
  → 经理:[X] 万
  → 总监:[X] 万
  → CFO:[X] 万
  → CEO:> [X] 万

□ 采购付款(需匹配合同签署权限):
  → 单笔 < [X] 万:经理
  → [X] 万 ≤ 单笔 < [X] 万:总监
  → [X] 万 ≤ 单笔 < [X] 万:CFO
  → ≥ [X] 万:CEO + 董事会

□ 合同签署(按合同金额):
  → < [X] 万:总监
  → [X] 万 ≤ < [X] 万:CFO
  → ≥ [X] 万:CEO + 董事会

第三步:定义审批路径

串行审批(单线审批):

□ 适用场景:标准费用报销、日常采购付款
□ 审批路径:申请人 → 直属上级(L1)→ 部门负责人(L2)→ [财务审核] → [CFO(如需)]

并行审批(多人会签):

□ 适用场景:高风险支出、跨部门预算
□ 审批路径:申请人 → 业务负责人 + 财务负责人 同时审批
□ 会签完成条件:[所有人通过 / 任意一人否决]

加权审批(金额累积):

□ 适用场景:供应商付款(同一供应商累计)
□ 规则:单笔 [X] 万,但同一供应商 30 天内累计 [X] 万须升级审批

第四步:特殊审批规则

例外审批规则:

□ 紧急审批(事后补批):
  → 触发条件:[紧急情况定义]
  → 审批权限:上级 [X] 人同时批准
  → 事后补批期限:[X] 天
  → 记录要求:[描述]

□ 超限额审批:
  → 超限 [X]% 以内:需 [上一级] 额外批准
  → 超限 [X]% 以上:需 [上两级] 批准
  → 超限 [X]% 且无合理解释:拒绝并要求重提

□ 关联方交易:
  → 所有关联方交易:须独立董事审批
  → 金额 > [X] 万:须董事会审批

□ 境外子公司:
  → 须同时满足当地法规和集团审批要求
  → 超出当地授权限制:上报集团审批

Read the full file on GitHub · 235 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. 9d ago First seen · 235 lines · 93 tokens per session scan A 0f56131403b0

Subscribe to this mod's changes

approval-matrix is a skill published in the GitHub repository vivy-yi/finance-skills (29 stars, last pushed 3mo ago), licensed MIT. It adds 93 tokens to every session and 2,196 once invoked, about $0.0005 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.

Related

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.

aden-hive/hive · 36 tokens

iso-13485-certification

Comprehensive toolkit for preparing ISO 13485 certification documentation for medical device Quality Management Systems. Use when users need help with ISO 13485 QMS documentation, including (1) conducting gap analysis of existing documentation, (2) creating Quality Manuals, (3) developing required procedures and work…

foryourhealth111-pixel/Vibe-Skills · 126 tokens

compliance-tracker

Track regulatory compliance for construction projects. Monitor permits, certifications, inspections, and regulatory requirements with automated alerts and reporting.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 28 tokens

safety-inspection-checklist

Digital safety inspection checklists for construction sites. Generate, conduct, and track safety inspections with automated reporting and compliance monitoring.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 31 tokens

delay-analysis

Analyze construction schedule delays for claims and recovery. Perform time impact analysis, identify delay causes, calculate damages, and document for disputes.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 29 tokens

change-order-manager

Manage construction change orders from request to approval. Track costs, schedule impacts, and maintain audit trail for dispute prevention.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 27 tokens