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 QuickerHub/quicker-rpc --skill quicker-action-library-searchgit clone --depth 1 https://github.com/QuickerHub/quicker-rpcWrote 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/quickerhub/quicker-rpc/quicker-action-library-search)<a href="https://agentmods.dev/skills/quickerhub/quicker-rpc/quicker-action-library-search"><img src="https://agentmods.dev/badge/skills/quickerhub/quicker-rpc/quicker-action-library-search/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/quickerhub/quicker-rpc/quicker-action-library-search"><img src="https://agentmods.dev/badge/skills/quickerhub/quicker-rpc/quicker-action-library-search.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 | $0.00044 | $0.00689 |
| Opus 5 | $0.00022 | $0.00345 |
| Sonnet 5 | $0.00009 | $0.00138 |
| Haiku 4.5 | $0.00004 | $0.00069 |
Grade A, and why
quicker-action-library-search 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 11d 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
动作库搜索与学习（quicker-action-library-search）
父 skill：quicker-authoring · 设计：
docs/authoring-references/getquicker-library-search/DESIGN.md
何时加载
- 从公开动作库找标杆、学习别人怎么写
- Phase 3 pattern 蒸馏需要 exemplar
- 用户问「动作库有没有…」
核心原则
- 只读学习：分享/库动作用
shared get拉取，禁止 patch - API 出口：走 qkrpc，Agent 不自己爬 HTML
- 自己写：
action create新建本地动作再patch
推荐调用
# 1) 搜公开库
qkrpc action library search --keyword "选中文本" --limit 10 --json
# 2) 只读拉程序体（压缩后）
qkrpc action shared get --id <sharedActionId> --return-mode full --json
# 响应含 readOnly:true, patchAllowed:false
MCP：qkrpc_action_library_search、qkrpc_action_shared_get。
本机已安装（辅助）
qkrpc action list --query '{"filter":{"source":"library"},"keyword":"…"}' --json
qkrpc action get --id <localActionId> --return-mode full --json
# 若 source=library 且 UseTemplate → 同样禁止 patch
shared get 之后
- 分析
compressed.steps/variables→ pattern 文档 - 不要
action patch/workspace_program写回 sharedActionId - 实写验证：
action create→ patch 到 新 localActionId →action run --trace→ 删除
实现状态回退（仅 qkrpc 不可用时）
| 步骤 | 临时 |
|---|---|
| 搜索 | 开发探针 npm run search:library -- --keyword "…" --json |
| 拉体 | 本机已装 → action get；否则修复 qkrpc 连接 |
禁止 Agent 用 WebFetch 自行解析 Search 页（解析必须在 qkrpc 内完成）。
硬规则
sharedActionId/ 库动作：只读，不得 patch- 新动作写作 → quicker-authoring P1 create + P6 patch（local）
- 单次搜索
--limit≤20，≤3 页
深度阅读
getquicker-library-search/DESIGN.mdgetquicker-library-search/SPEC.mddocs/quicker-action-data-storage.md§10（GetSharedActionAsync）
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.
- 11d ago First seen · 73 lines · 44 tokens per session scan A a874e6e7ba23
quicker-action-library-search is a skill published in the GitHub repository QuickerHub/quicker-rpc (13 stars, last pushed 28d ago), licensed MIT. It adds 44 tokens to every session and 689 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
gws-events
Subscribe to Google Workspace events.
gws-events-renew
Google Workspace Events: Renew/reactivate Workspace Events subscriptions.
gws-script-push
Google Apps Script: Upload local files to an Apps Script project.
voiden
Create and edit Voiden .void files for API testing. Covers the .void file format and all enabled extension block types.
agent-desktop-ffi
C-ABI bindings over agent-desktop's PlatformAdapter. Consumers (Python ctypes, Swift, Node ffi-napi, Go cgo, C++, Ruby fiddle) link libagentdesktopffi.{dylib,so,dll} and call ad functions directly instead of spawning the CLI binary per call. The canonical observe-act workflow is: adinit → adadaptercreate[withsession]…
api-design
A guide to designing web APIs—the interfaces that let software systems exchange data—using REST, gRPC, and GraphQL patterns.