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-authoring-getquicker-user-actionsgit 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-authoring-getquicker-user-actions)<a href="https://agentmods.dev/skills/quickerhub/quicker-rpc/quicker-authoring-getquicker-user-actions"><img src="https://agentmods.dev/badge/skills/quickerhub/quicker-rpc/quicker-authoring-getquicker-user-actions/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-authoring-getquicker-user-actions"><img src="https://agentmods.dev/badge/skills/quickerhub/quicker-rpc/quicker-authoring-getquicker-user-actions.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 | $0.00052 | $0.01614 |
| Opus 5 | $0.00026 | $0.00807 |
| Sonnet 5 | $0.00010 | $0.00323 |
| Haiku 4.5 | $0.00005 | $0.00161 |
Grade A, and why
quicker-authoring-getquicker-user-actions 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
getquicker 用户动作获赞统计(quicker-authoring-getquicker-user-actions)
父 skill:quicker-authoring · 状态:promoted · 参考:QuickerBench
user-action-likes-total
何时加载
从 getquicker.net User/Actions 分享页(含分页)抓取公开动作列表,汇总 获赞总数 与 动作个数,写入输出变量。不要 msgbox / textwindow / form。
步骤骨架
- 输入:动作参数
quicker_in_param(完整 URL 或User/Actions/…路径) - 规范化 URL:
sys:evalexpression或sys:assign— 补https://getquicker.net/前缀,去掉尾部?p= - 首页 GET:
sys:httpmethod GET → 变量pageHtml/httpContent - 解析分页:从首页 HTML 取
maxPage(链接里?p=(\d+)最大值,通常 1–5)和可选共 (\d+) 个动作 - 分页循环:
sys:repeat(stopCondition或固定次数)或page=1..maxPage- 每页 GET:
baseUrl或baseUrl?p={page}(第 1 页可无 query) - Bench/mock:HTTP 由 mock profile 注入 fixture HTML — 勿 web_search / browser
- 每页 GET:
- 解析表格:每页 HTML 中
<tr>含Sharedaction?code=的行 → 取 第二个 数字列(likes)- 推荐单步
sys:evalexpression+ C#Regex.Matches累加;复杂 C# 放files/*.eval.cs再file_write+ patch
- 推荐单步
- 输出变量:
totalLikes、actionCount设 IsOutput=true
硬规则(本场景)
step_runner_search→get:http|regexExtract|repeat|evalexpression|assign— 可多次 search 不同模块,禁止猜inputParams。- 子程序式:结果只写 输出变量;禁止弹窗展示结果。
repeat/each子步骤挂ifSteps;单分支用simpleIf。- patch 后
workspace_program diagnostics— 禁止read_data验证;mock assert 会检查输出变量。 - 大段 C#(含
{})勿内联进qkrpc_action_createJSON — 用workspace_program file_write写.eval.cs。
HTML 提示(113342-Cea fixture)
- 分页链接:
?p=2…?p=5;首页文本共 117 个动作 - 数据行:
<tr>含Sharedaction?code=(跳过含<th的行) - 获赞在
class="align-middle text-center d-none d-md-table-cell small"的 第一个 数字单元格(不是「点赞」文本) - 表头列顺序:… 大小(非 small 纯数字 td)→ 获赞 → 用户
推荐解析(与 QuickerBench oracle 一致)
files/parsePage.eval.cs — 每页 HTTP 后执行,累加 totalLikes / actionCount,首次页还可算 maxPage:
var rows = System.Text.RegularExpressions.Regex.Matches(pageHtml, @"<tr>[\s\S]*?</tr>");
int pageLikes = 0, pageCount = 0;
foreach (System.Text.RegularExpressions.Match rm in rows)
{
var row = rm.Value;
if (!row.Contains("Sharedaction") || row.Contains("<th")) continue;
var cells = System.Text.RegularExpressions.Regex.Matches(
row,
@"<td class=""align-middle text-center\s+d-none d-md-table-cell small"">([\s\S]*?)</td>");
if (cells.Count < 1) continue;
var likesRaw = System.Text.RegularExpressions.Regex.Replace(cells[0].Groups[1].Value, @"<[^>]+>", "").Trim();
if (int.TryParse(likesRaw, out var likes)) { pageLikes += likes; pageCount++; }
}
{totalLikes} = {totalLikes} + pageLikes;
{actionCount} = {actionCount} + pageCount;
if ({maxPage} <= 1)
{
int mp = 1;
foreach (System.Text.RegularExpressions.Match m in System.Text.RegularExpressions.Regex.Matches(pageHtml, @"[?&]p=(\d+)"))
mp = System.Math.Max(mp, int.Parse(m.Groups[1].Value));
{maxPage} = mp;
}
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 · 114 lines · 52 tokens per session scan A 05a51ff71f05
quicker-authoring-getquicker-user-actions is a skill published in the GitHub repository QuickerHub/quicker-rpc (13 stars, last pushed 28d ago), licensed MIT. It adds 52 tokens to every session and 1,614 once invoked, about $0.0003 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-modelarmor
Google Model Armor: Filter user-generated content for safety.
persona-event-coordinator
Plan and manage events — scheduling, invitations, and logistics.
persona-team-lead
Lead a team — run standups, coordinate tasks, and communicate.
persona-researcher
Organize research — manage references, notes, and collaboration.
recipe-plan-weekly-schedule
Review your Google Calendar week, identify gaps, and add events to fill them.
recipe-review-meet-participants
Review who attended a Google Meet conference and for how long.