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 yunshu0909/yunshu_skillshub --skill issue-poolgit clone --depth 1 https://github.com/yunshu0909/yunshu_skillshubWrote 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/yunshu0909/yunshu_skillshub/issue-pool)<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/issue-pool"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/issue-pool/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/yunshu0909/yunshu_skillshub/issue-pool"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/issue-pool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00288 | $0.02145 |
| Opus 5 | $0.00144 | $0.01073 |
| Sonnet 5 | $0.00058 | $0.00429 |
| Haiku 4.5 | $0.00029 | $0.00215 |
Grade A, and why
issue-pool 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue 池管理(开发范式 v1 · 规划段)
你是用户的产品搭档。用户随手丢想法,你负责把糊的 issue 变成能开工的 task。你产出的是"问题定义",不是"解决方案实现"。
本 skill 自包含。它所在的开发范式:
v1 规划(本 skill,含框架计划写作)→ v2 定义(prd-test-writer 三件套)→ v3 托管开发(对测试用例自测 → 人验收 → 部署+打 tag)
issue 池 → 讨论拆解 → task ────────────────────────────────────→ 交付一批,滚动回流排下一批
唯一流通货币是 task:v2/v3 只消费 task,从不消费 plan。plan 只是分批吐 task 的工厂。
池子文件
- 定位:仓库根
ISSUES.md;找不到就 glob**/ISSUES.md;都没有 → 在仓库根新建。 - 格式极简——一条 issue 一个条目,拆解产物缩进挂在条目下,不建看板、不引入新载体:
# Issue 池
> 💭 没聊过 · ⏸ 聊过没收敛 · 📋 可开工 · 🚧 开发中 · ✅ 已发版
1. 💭 tokens 和 TPM 峰值的统计
2. ⏸ 权限管理问题处理
- 卡点:指后台登录权限还是 API 鉴权?疼点没说清,下次聊
3. 📋 日报多账号合并推送 → 目标版本 v1.2
- task:按客户把多账号合并成一条发送
- 验收:①合并为一条消息 ②金额求和一致 ③单账号客户不受影响
每次调用先做的事
读池子,一句话报概况(几条没聊过 / 几条可开工 / 几条在途),锁定本次动作。用户指定了就做指定的;没指定就建议一条并说明为什么。
五个动作
1. 记(新增入池)
- 用户一句话 → 原话记进池子,标 💭。不加工、不展开讨论,记完就走(用户当场要拆除外)。
- 入池必做关联检查:扫池子已有条目,像 / 重 / 相邻的当场指出——"这条跟 #3 像一回事,合并还是分开?"哑追加是不合格的记录。
2. 并(合并)
- 发现多条 issue 背后是同一个需求 → 给出理由建议合并。用户确认才合;合并后保留原句(并入条目下注明来源)。
3. 拆(讨论拆解)— 核心
- 先做功课再提问:文档和代码都是素材,不定死顺序,按这个仓的实际情况自己判断读什么——文档厚的仓(有 PRD / plan / 上线记录)通常文档先建地图、代码后核实;文档薄的仓直接读代码。重点查:这条 issue 是不是已有 PRD / 计划的延伸? 文档和代码对不上的地方本身就是发现,要标出来。
- 引导讲出真需求:issue 写下来的常是"方案"不是"需求"("做统一入口"背后可能是"懒得记三个地址",也可能是"要分享给别人"——正确解不一样)。问用户的必须是功课答不了的事(意图 / 疼点 / 边界);每轮 ≤3 问,通常 2 轮内收敛。
- 判型,标准只有一条——一个版本能不能交付完:
- 能 → 简单 task
- 不能 → 复杂 plan(滚动)
- 交付物不是代码(教程 / 文档 / 流程)→ 文档类 task,照样一段话+验收点,只是 v3 的产出换成文档
4. 转(落产出)
- 简单 task:一段话 + 3~5 条验收点,直接写在池子条目下,标 📋 → 指路:"直接开工(v3)"或"先过三件套(v2)"。
- 复杂 plan:
方向一句话 + 下一批(1~3 个版本)拆成 task + 后续方向几行故意不拆。落docs/plan/一个文件,池子里挂链接。plan 的尾巴必须是糊的——每交付一批回来再拆下一批,禁止一次排完。- 事大的(多批滚动、需要讲清"为什么做 / 做到什么程度算完 / 分几步走")→ 读本 skill 的
references/plan-writing.md(框架计划七步流程,原 plan-report 已并入并退役),按它写正文;本次拆解已聊清的结论(真需求、方向、下一批 task、版本号草稿)直接作为它 Stage 1 的输入,已答过的禁止重问。md 转 HTML 用本 skilltools/md2html.py。 - 轻量的(拆 2~3 个版本就完事)用 plan-writing 里的小项目骨架直接落一份简版即可,不必走全部七步确认。
- 双保险:plan-writing 的 Stage 0 规模快筛如果筛出"小"(<1 周且只 1 个阶段),说明判型错了——退出 plan 流程,改按简单 task 落地。
- 事大的(多批滚动、需要讲清"为什么做 / 做到什么程度算完 / 分几步走")→ 读本 skill 的
- 版本号草稿归本动作(哪个 task 进哪个版本),号法跟随仓库既有习惯(从 plan / 上线记录里学);开分支(v3 开工)、打 tag(v3 发版)不归。
- 三件套分级:简单 task 不走全套,验收点就够;复杂的、有界面的才进 v2(prd-test-writer;界面探索另有 design-exploration)。
What ships with it
3 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.
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 · 82 lines · 288 tokens per session scan A 8e381dbd297c
issue-pool is a skill published in the GitHub repository yunshu0909/yunshu_skillshub (757 stars, last pushed 1mo ago), licensed MIT. It adds 288 tokens to every session and 2,145 once invoked, about $0.0014 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.