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 agents/cxtx/finance-copilot-skills/claude-codegit clone --depth 1 https://github.com/cxtx/finance-copilot-skillsWhat 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 | $0.00000 | $0.00468 |
| Opus 5 | $0.00000 | $0.00234 |
| Sonnet 5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
claude-code 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 2d 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.
What it actually says
Claude Code 平台专属配置
平台专属适配说明（安装 / 发现 / 调用 / 权限 / 网络限制），不含对账业务逻辑（NFR-08）。 支持级别：格式兼容（未逐项实测），验证项清单见 docs/governance/agent-install.md §4。
安装位置
| 范围 | 目标目录 |
|---|---|
| 用户级 | ~/.claude/skills/fcs-reconcile/ |
| 项目级 | <项目根>/.claude/skills/fcs-reconcile/ |
安装方式统一走提示词，见 README「安装」。装完须新开会话才加载。
运行约定
- 入口：
scripts/reconcile.py --config <config.yaml> - 解释器：必须是装过
requirements.txt（pandas/openpyxl/pyyaml）的那一个； 与安装依赖时用的解释器不一致的表现是ModuleNotFoundError: pandas。 - 网络：运行期禁用——
guard.block_network()在管线第一步执行，外连抛NetworkDisabledError。仅安装期（装依赖）需要网络。 - 文件访问：仅用户在配置里指定的输入与输出路径；源文件只读，运行前后 SHA-256 比对； 输出路径覆盖输入时直接拒绝执行。
- 上交给模型的内容：只有
summary（匹配率、各状态计数、勾稽结论）。 原始明细、DataFrame、标准行不越界，终端也不打印交易明细。
运行前确认
Skill 须先展示数据处理声明（读写文件数、原始数据是否进模型、网络状态、源文件是否修改、
输入完整性校验）并等待用户确认，确认前不落盘。声明格式见 SKILL.md「数据处理声明」。
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.
- 2d ago First seen · 32 lines · 0 tokens per session scan A 1a1bf340af3c
claude-code is an agent published in the GitHub repository cxtx/finance-copilot-skills (2 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 468 tokens. 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 agents, from other repositories
claude-code
Agent "claude-code" from cynco-labs/ai-accounting-skills, covering claude code, install skills, option a — skills.sh (recommended multi-agent path), option b — plugin marketplace (umbrella + hooks) and firm profile.
codex
Agent "codex" from cynco-labs/ai-accounting-skills, covering codex (openai), install, or project-local, firm profile and workflow.
cursor
Agent "cursor" from cynco-labs/ai-accounting-skills, covering cursor, install, firm profile, workflow and notes.
glm
Agent "glm" from cynco-labs/ai-accounting-skills, covering glm, install, cli backbone, firm profile and practice notes.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.