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/gongxuanzhang/shengsheng-skill/github-issue-solution-loopnpx skills add gongxuanzhang/shengsheng-skill --skill github-issue-solution-loopgit clone --depth 1 https://github.com/gongxuanzhang/shengsheng-skillWrote 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/gongxuanzhang/shengsheng-skill/github-issue-solution-loop)<a href="https://agentmods.dev/skills/gongxuanzhang/shengsheng-skill/github-issue-solution-loop"><img src="https://agentmods.dev/badge/skills/gongxuanzhang/shengsheng-skill/github-issue-solution-loop.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 | $0.00143 | $0.02242 |
| Opus 5 | $0.00072 | $0.01121 |
| Sonnet 5 | $0.00029 | $0.00448 |
| Haiku 4.5 | $0.00014 | $0.00224 |
Grade A, and why
github-issue-solution-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Issue Solution Loop
持续 review GitHub issue，从问题理解到方案一致，再等待作者或维护者提交关联 PR 并 review PR。核心原则：只讨论方案和 review，不写代码、不建分支、不开 PR。
身份与工具约束
- GitHub 操作必须使用本地
gh命令。 - 如果本机没有
gh，先安装gh，再继续。 - GitHub 身份必须来自本地环境变量
GITHUB_BOT_TOKEN。 - 不使用本机已有的个人
gh auth登录态。 - 不使用其他账号或 token。
- 不打印、不 echo、不暴露 token。
- 在 Codex 客户端中需要持续观察时，优先使用 heartbeat automation 做真正后台轮询，不只依赖一个前台 sleep loop。
- 禁止写代码、改文件、建分支、commit、push、开 PR 或更新 PR 内容。
- 方案达成一致后，只要求 issue 作者或维护者提交/更新 PR，然后等待并 review。
- review 关联 PR 时不执行测试命令；默认 PR 提交流程或 CI 已经跑过必要测试，只从代码和 diff 判断测试覆盖是否足够。
- 推荐命令形式：
GH_TOKEN="$GITHUB_BOT_TOKEN" gh issue view <issue>
GH_TOKEN="$GITHUB_BOT_TOKEN" gh issue comment <issue> --body "<body>"
GH_TOKEN="$GITHUB_BOT_TOKEN" gh pr view <pr>
如果 GITHUB_BOT_TOKEN 不存在，停止并要求用户提供；不要降级使用个人账号。
Loop 参数
- 默认持续时间：用户未指定时运行 2 小时。
- 默认范围：用户指定的 issue。
- 如果用户要求扫描多个 issue，每轮都重新查询目标范围，不能因为上轮数量固定就提前停止。
- 优先创建或更新挂在当前 Codex session 上的 heartbeat automation；每次唤醒执行一轮 issue/PR 扫描，然后交回给 automation 调度下一轮。
- 根据当前 active issue 或关联 PR 更新当前 Codex session 标题；如果运行环境没有 session 标题控制能力，则跳过，不影响 loop。
- 如果某轮发布了 issue comment 或执行了 PR review/comment，立刻开始下一轮扫描。
- 如果某轮没有任何动作，等待 5 分钟 后再扫描。
- 到达持续时间后停止，并总结：
- issue 当前状态
- 方案是否已达成一致
- 已处理的相关 PR
- 已 approve 的 PR
- 仍阻断的问题
- 跳过或未执行动作的原因
每轮必须检查
对 issue 收集：
- issue number、title、body、author、labels、assignees、state、updatedAt
- 最新 issue comments
- bot 上一次 issue comment/action
- linked PR、closing references、timeline events
- 是否有新评论、维护者信号、作者回复、label 变化或其它更新
对相关 PR 收集：
- PR head SHA、commit 列表、评论、review comments、reviews
- bot 针对当前 head SHA 的上次 review 状态
- 上次 review 之后是否有新提交、评论、回复或 review
常用命令示例：
GH_TOKEN="$GITHUB_BOT_TOKEN" gh api user --jq .login
GH_TOKEN="$GITHUB_BOT_TOKEN" gh issue view <issue> --json number,title,body,author,comments,labels,assignees,state,updatedAt
GH_TOKEN="$GITHUB_BOT_TOKEN" gh api repos/<owner>/<repo>/issues/<issue>/timeline
当 gh issue view 信息不足时，用 gh api 查询 timeline 或 linked PR。
Codex 后台轮询
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.
- 5d ago First seen · 216 lines · 143 tokens per session scan A 222f8c892755
github-issue-solution-loop is a skill published in the GitHub repository gongxuanzhang/shengsheng-skill (10 stars, last pushed 1mo ago), licensed MIT. It adds 143 tokens to every session and 2,242 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…