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 Viy1204/recruiting-copilot --skill recruit-boardgit clone --depth 1 https://github.com/Viy1204/recruiting-copilotWrote 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/viy1204/recruiting-copilot/recruit-board)<a href="https://agentmods.dev/skills/viy1204/recruiting-copilot/recruit-board"><img src="https://agentmods.dev/badge/skills/viy1204/recruiting-copilot/recruit-board/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/viy1204/recruiting-copilot/recruit-board"><img src="https://agentmods.dev/badge/skills/viy1204/recruiting-copilot/recruit-board.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 | $0.00096 | $0.01753 |
| Opus 5.5 | $0.00038 | $0.00701 |
| Sonnet 5.5 | $0.00019 | $0.00351 |
| Haiku 4.5 | $0.00010 | $0.00175 |
Grade A, and why
recruit-board 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 today.
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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
招聘进展看板
先确认用户要看的工作区，定位本 skill 所在目录；读取该工作区的台账、岗位表、可选映射与独立进度文件。候选资料按点击读取，岗位状态仅在用户保存时更新本地岗位表。源码维护目录没有台账时，不自动创建候选资料或打开空面板。
打开与开工
Claude Desktop、Codex App、WorkBuddy 默认使用同一网页。先读取 references/hosts.md，按“记录真实步骤 → connect 探测 → 必要时宿主管理前台服务并复核 → 打开或复用网页并交付本轮链接”交接，在耗时寻源前让用户看到本轮动态。首次默认打开 live 首页，明确指定本轮时才固定 run。只查看看板不 start；源码维护也不创建招聘 run。
只有 connect 返回 ready 才可复用服务；使用它返回的完整 url / runUrl，保留工作区键与 run 参数。宿主有专用服务、Browser/Preview 工具时使用实际工具，没有打开工具就给明确本机链接；不承诺自动右侧停靠。Claude 原生 /recruiting-board 保留为手动可选入口，单一内容源加载和降级规则也见 hosts；主 skill /recruit-board 负责使用指引，不每轮自动开两份 UI。
读数边界
- 记录数只取
02-sourcing/dedup-ledger.csv，每个姓名＋原岗位计一次；同人不同原岗位不自动合并。阶段按当前状态精确映射。状态或评级冲突保留原值并归未归类，不从备注、档案或来源轮次推断。 - 岗位只读
CONTEXT.md「在招岗位与优先级」表。默认显示在招＋未知岗位，范围可选“在招 / 关注 / 全部”；搜索只缩小岗位选项，不改变汇总。关注仅是按工作区隔离的个人偏好，不修改 CONTEXT；关闭岗位仍可在“全部”查看存量。未读取岗位配置时显示台账岗位且状态未知；缺失、错误、陈旧与正常空表明确区分。 - 可选
_shared/recruit-board.config.json以schemaVersion: 1、statusStages和roleAliases提供精确映射，格式见配置参考。状态键 trim＋英文小写，阶段值限STAGES中的 ID；岗位别名仅 trim 后完整匹配，目标须在本次成功读取的岗位表中，禁止链与循环。筛选用标准岗位名，原岗位仍显示；显式映射unclassified不报未识别状态。 - 无兼容配置时使用标准映射；首次配置非法则整份不应用并提示。曾成功应用的配置变坏或缺失时，候选、岗位与源时间整体保留并标陈旧，不能新旧混算。配置字典与说明元数据不进入 HTTP 快照。
- 上部是工作区任务，未绑定 session 的 run 不代表左侧会话本轮。网页常规首页默认 live，按
createdAt跟随最新任务；带?run=<id>（或 helper 完整链接中的run参数）明确固定本轮，手动选择历史也固定。查看候选、完整结果或编辑岗位时新 run 不抢占，保留阅读位置并提供“回到最新”。没有 run 时显示“尚无任务进度记录”，不补造历史。 - 前台每 1 秒单飞轮询，不重叠请求；页面隐藏时降频，恢复可见立即读取。读取状态与业务“最后记录”分开，轮询成功不能说明任务进程存活，也不称实时心跳；异常退出不按超时猜完成或失败。
- 首页最近动态仅按需读取所选 run 的 3 条真实结果 body，不把候选结论塞进全量私密快照；完整结果与候选资料继续按需加载。演示记录只用隔离的演示工作区，不与真实记录混用。
- 本轮任务结果独立于下方台账筛选，按需显示处理过的人、实际结果和需确认事项；“本轮已记录 N 人”只表示收据覆盖数，未入账者也可显示结果但不冒认资料，读数与待确认规则见
references/progress.md。 - 全量快照仅含必要姓名、岗位、评级、原状态与阶段及任务 summary；结果短结论按需读取。点击候选后按原 ID 读取台账背景、备注、来源和已关联本地资料；资料正文不进入全量快照。不拖拽、不修改候选状态、不联系候选人，不连接 CDP、招聘网站或 DSH 面板。
候选资料与岗位管理
- 点击姓名查看资料，返回名单保留岗位、阶段和任务选择。仅支持工作区内 Markdown、TXT、PDF；Markdown 用安全文本元素显示，PDF 可独立打开或下载。外链、工作区外、可执行或不支持的文件明确标不可读。
- 台账简历路径按单个完整值解析，不拆分说明文字或猜附件。同名档案仅在姓名完整、全局唯一、姓名字段或标题一致、岗位精确匹配时自动关联；先核完整岗位名；完整值属于其他正式岗位或别名时绝不剥括号，只有未知尾注才可剥后精确核对。匹配档案的相对链接以档案目录解析。歧义可用
_shared/recruit-board.files.json精确指定，格式见配置参考；不扫描整个工作区找同名附件。 - 岗位旁“管理”只允许调整当前标准表中已配置岗位，状态限在招、已下架、已关闭、暂停、待核。保存更新本地
CONTEXT.md的一个状态单元格，保留其他原文、换行和编码并自动备份；不修改招聘平台岗位。取消不写入，版本冲突时重新读取后再保存。 - 原生通过
scripts/actions.mjs共用资料解析和岗位写入；成功输出 JSON 数据，失败输出 JSON 错误并返回非零。candidate／document／open-document只接原候选 ID 和资源 ID，role-info读取版本，role-set必须携带 revision。不能把任意路径或 shell 命令作为接口参数。
What ships with it
21 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .claude-plugin/plugin.json 283 B
- hooks/hooks.json 36 B
- hooks/register.tsx 70 KB
- model.mjs 34 KB runs code
- public/app.js 73 KB runs code
- public/index.html 14 KB
- public/live.mjs 2.6 KB runs code
- public/style.css 32 KB
- recruiting-board.test.ts 70 KB runs code
- references/configuration.md 4.7 KB
- references/hosts.md 8.0 KB
- references/progress.md 10 KB
- scripts/actions.mjs 3.9 KB runs code
- scripts/connect.mjs 4.9 KB runs code
- scripts/progress.mjs 5.6 KB runs code
- scripts/reader.mjs 3.0 KB runs code
- scripts/records.mjs 14 KB runs code
- scripts/results.mjs 3.4 KB runs code
- scripts/roles.mjs 7.3 KB runs code
- scripts/server.mjs 13 KB runs code
- types/index.d.ts 5.5 KB runs code
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.
- today First seen · 38 lines · 96 tokens per session scan A 50638bd1009d
recruit-board is a skill published in the GitHub repository Viy1204/recruiting-copilot (103 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 1,753 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-28.
Other skills, from other repositories
product-manager
A product-management guide covering work from discovering a need through launch and measurement. It includes tools such as PRDs, which describe a product requirement, and RICE, a method for ranking opportunities.
to-tickets
A task-planning method that breaks a plan, specification, or conversation into small tasks that can each be completed and checked independently.
product-sprint-prioritizer
A product-planning skill that ranks a list of requests with frameworks such as RICE, a method that compares reach, impact, confidence, and effort. It can also organize work into iterations or Sprints, which are fixed periods for completing a selected group of tasks.
promote-idea
Converts an album idea from IDEAS.md into an actual album project in one step. Use when the user says "promote [idea title]", "turn idea into album", or "start working on [idea]".
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…
customer-onboarding-and-implementation
Takes a new customer from signature to working — setting a definition of live that both sides agreed before the contract was signed, planning and staffing the implementation, running data migration and integration realistically, training the people who will actually use it, and handing over to the ongoing…