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 skills/tae0y/python-project-template/template-proposal-reviewnpx skills add tae0y/python-project-template --skill template-proposal-reviewgit clone --depth 1 https://github.com/tae0y/python-project-templateWhat 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 | $0.01369 |
| Opus 5 | $0.00000 | $0.00685 |
| Sonnet 5 | $0.00000 | $0.00274 |
| Haiku 4.5 | $0.00000 | $0.00137 |
Grade C, and why
template-proposal-review scanned grade C with 1 finding 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 yesterday.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/tmp.XXXXXX The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- yesterday First seen · 175 lines · 0 tokens per session scan C a3ab998d3f55
template-proposal-review is a skill published in the GitHub repository tae0y/python-project-template (14 stars, last pushed 25d ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 1,369 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other skills, from other repositories
login_auto
基于 Supabase Auth + Resend SMTP 实现通用登录系统，零新依赖。覆盖邮箱密码登录、OAuth(google/github)、邮箱验证码注册、邮箱验证码改密。验证码邮件经 Supabase 自定义 SMTP 接入 Resend 投递。当用户说"loginauto"、"登录实现"、"Supabase登录"、"通用登录"时触发。.
init
初始化 cc-code 极简开发工作流场域。三轨判定(新建/已最新/升级迁移) → 生成 .cccode/ 黑匣子目录树与模板骨架 → 旧版场域按「归档→清点→迁移→校验→归位」升级到当前插件规范(全程零删除) → 进入角色串行状态机循环。.
next2taro
将 Next.js (App Router + Tailwind + shadcn/ui) 的 UI 页面/组件转换为 Taro 小程序 (View/Text + SCSS + PNG)。当用户说"next2taro"、"转换页面"、"Next转Taro"、"页面迁移" 时触发。.
plan-prd-feature
⭐显式触发的【增量需求规划器】（MVP 已交付后做功能迭代用）。触发后【第一动作必须 call EnterPlanMode 工具】（不许先做任何其他动作）。plan 内：规范体检 → 锁基线（status/gates/prd 历史）→ codegraph 四路侦察（explore 读现状 + impact 算传递闭包半径 + files 对账目录 + affected 算测试面，前置新鲜度保险）→ 需求逐点三态判定（已实现/无冲突/有冲突）→ 冲突逐条硬门控裁决 → 输出三件套（逻辑图+原型双联+带落盘路由的差异表）→ 逐点循环至通顺 → 主人验收后 ExitPlanMode →…
whole-qa
❌ 错：whole-qa 自己测、自己修 → 测的人知道修的人怎么想，修的人知道测的人怎么测 → 互相糊弄 ✅ 对：whole-qa 只做 清点 / 分发 / 汇总 / 循环控制.
agent-to-mvp
启动校准 → ①PM → 校准 → ②Architect → 校准 → ③Dev → 校准 → ④QA → 校准 │ ┌─────────┴──────────┐ ▼ ▼ FAIL→回Dev(≤3) PASS→阶段结算→校准 │ │ 3轮仍FAIL→升级 ▼ (回prd-plan/人) 还有阶段? →回① 全PASS → MVP收口.