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/whynusn/typetype/typetype-docs-syncnpx skills add whynusn/typetype --skill typetype-docs-syncgit clone --depth 1 https://github.com/whynusn/typetypeWrote 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/whynusn/typetype/typetype-docs-sync)<a href="https://agentmods.dev/skills/whynusn/typetype/typetype-docs-sync"><img src="https://agentmods.dev/badge/skills/whynusn/typetype/typetype-docs-sync.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 | $0.00000 | $0.00585 |
| Opus 5 | $0.00000 | $0.00293 |
| Sonnet 5 | $0.00000 | $0.00117 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade A, and why
typetype-docs-sync 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 6d 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
文档同步操作手册
在大量代码修改或重构后，使文档与代码保持一致。
触发方式
在对话中说：
"同步文档" 或 "sync docs"
AI Agent 应执行本手册的全部步骤。
同步流程
第 1 步：识别变更范围
# 查看当前分支与 main 的差异（文件级）
git diff main...HEAD --stat
# 查看具体变更内容
git diff main...HEAD
分类变更类型：
| 变更 | 涉及文档 |
|---|---|
| 新增/删除/重命名 Python 源文件 | ARCHITECTURE.md § 目录结构 |
| 新增/删除 QML 页面 | docs/reference/qml-pages.md |
| 修改 Bridge Slot/Signal | docs/reference/bridge-slots.md |
| 修改 API 端点 | docs/reference/api-endpoints.md |
| 新增配置字段 | docs/reference/config.md |
| 新增编码陷阱 | AGENTS.md § 已知陷阱 |
| 新增架构决策 | docs/decisions/ 新建架构决策记录 |
| 架构/分层变更 | ARCHITECTURE.md 相关章节 |
第 2 步：更新对应文档
原则：指向不复制。如果需要引用另一个文档的信息，用链接，不要复制内容。
第 3 步：验证
验证清单见 docs/meta/README.md § 验证清单。
# 关键检查：所有链接有效
# 现有技巧：用编辑器打开 affected .md 文件，点击链接验证
# CLAUDE.md 必须 ≤15 行
wc -l CLAUDE.md # 应 ≤15
# AGENTS.md 和 ARCHITECTURE.md 陷阱无重叠
# 人工检查：AGENTS.md §8 是编码实践类，ARCHITECTURE.md §已知陷阱 是架构设计类
第 4 步：提交
文档更新与代码修改应在同一个 PR/提交中。
典型场景
场景：重构后同步
用户："同步文档"
AI：执行上述 1-4 步
场景：新增功能后同步
用户：feat: 新增 xxx 功能，同步文档
AI：执行上述 1-4 步
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.
- 6d ago First seen · 80 lines · 0 tokens per session scan A b12284a70e09
typetype-docs-sync is a skill published in the GitHub repository whynusn/typetype (11 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 585 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 2026-08-30.
Other skills, from other repositories
add-crate
Add a new member crate to a Cargo workspace in this repo using the y5-template binary. Use whenever the user asks to add/create/scaffold a new crate, module, or workspace member (e.g. "add a crate under compositor.window", "scaffold action.foo"). Handles the chain-prefix naming convention and non-interactive…
logging
How to log in the y5 compositor. Use whenever you add, change, or migrate logging — any time you'd reach for a log/print statement, "add a log", debug output, tracing::!, println!, or a fatal panic! with a message. y5 has its own tracing-free structured logging; this skill is the source of truth for using it.
perf-audit
Full performance/concurrency audit of Unisic (C++/Qt6/QML, Wayland). Use when the user asks for a performance audit, "make app fast", idle CPU/memory investigation, memory leaks, thread bugs, deadlocks, or invokes /perf-audit. Measurement-first — never guess; produces a structured report and minimal fixes.
ponytail-perf-audit
Ponytail-style performance/concurrency audit of Unisic (C++/Qt6/QML, Wayland): lazy senior engineer, evidence-first, NO code changes during the audit. Produces a verdict/baseline/ranked-findings report in the strict P tag format. Use when the user says "ponytail audit", "audyt wydajności ponytail"…
analyzing-linux-elf-malware
Analyze malicious Linux ELF binaries — botnets, cryptominers, ransomware, and rootkits targeting Linux servers, containers, and cloud infrastructure — through static analysis, dynamic tracing, and reverse engineering of x8664 and ARM samples. Use when investigating Linux malware, triaging a suspicious ELF binary…
analyzing-linux-kernel-rootkits
Detect kernel-level rootkits in Linux memory dumps using Volatility3 linux plugins (checksyscall, lsmod, hiddenmodules), rkhunter system scanning, and /proc vs /sys discrepancy analysis to identify hooked syscalls, hidden kernel modules, and tampered system structures.