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/donglistudio/personal-agent-foundation/github-clinpx skills add DongLiStudio/personal-agent-foundation --skill github-cligit clone --depth 1 https://github.com/DongLiStudio/personal-agent-foundationWhat 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 | $0.00109 | $0.01031 |
| Opus 5 | $0.00055 | $0.00515 |
| Sonnet 5 | $0.00022 | $0.00206 |
| Haiku 4.5 | $0.00011 | $0.00103 |
Grade A, and why
github-cli 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 3d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub CLI
使用 gh 处理 GitHub 托管状态和协作流程。使用本地 git 处理本地仓库状态、diff、分支、commit 和 remote。优先使用官方 gh 子命令;只有高层命令无法满足时才使用 gh api。
安全起步
- 使用
gh前先确认目标仓库。在本地仓库中检查git remote -v;不在仓库中时,要求或推断OWNER/REPO,并传入-R OWNER/REPO。 - 执行 GitHub 操作前先检查认证:
gh auth status - 多账号场景下,如可用,先读取
{{AGENT_ROOT}}\GLOBAL\GITHUB_ACCOUNTS.md,再确认 active 账号与目标项目或用户意图匹配。 - 如果 active 账号不对,不要继续写操作。显式切换账号:
gh auth switch --hostname github.com --user <username> - 除非用户明确要求诊断凭据,否则不要打印或索要 token。避免使用
gh auth token和gh auth status --show-token。 - 涉及账号新增、重新授权、默认/专属账号路由、换机恢复、安全退出、远程仓库创建或首次 push 时,读取 references/account-routing.md。
先读后写
任何写操作前,先用只读命令建立上下文:
gh repo view OWNER/REPO
gh issue view 123 -R OWNER/REPO --comments
gh pr view 123 -R OWNER/REPO --comments
gh pr checks 123 -R OWNER/REPO --json bucket,completedAt,link,name,state,workflow
gh run list -R OWNER/REPO
gh run view <run-id> -R OWNER/REPO --log
优先使用 --json 配合 --jq 或模板获得机器可读结果。命令支持 --web 时,除非用户希望打开浏览器,否则不要使用。
写操作和确认
以下操作必须有明确用户意图后再执行:创建/编辑/关闭 Issue 或 PR、PR 评论/Review、push 分支、merge PR、创建/发布/删除 Release、workflow dispatch/rerun/cancel、Secret 或 Variable 变更、仓库创建/删除/归档/可见性变更、deploy key、SSH/GPG key,以及 GitHub CLI extension/skill 安装。
高影响写操作前,说明目标账号、仓库、操作和主要参数。可行时先使用非变更预览,例如 gh pr diff、gh pr view、gh release view、gh workflow view、gh api --method GET。
常见工作流
任务涉及 PR、Issue、Actions/CI、Release、gh api 或 GitHub CLI skills 时,读取 references/commands.md 获取具体命令模式。账号生命周期、项目路由、remote 与首次 push 读取 references/account-routing.md。
错误处理
- 如果找不到
gh,在 Windows 上先检查%LOCALAPPDATA%\Programs\GitHub CLI\gh.exe,再询问是否安装或修复 PATH。 - 如果尚未登录,运行
gh auth login --hostname github.com --git-protocol https --web,并把浏览器/设备授权指引返回给用户。 - 如果缺少 scopes,先说明为什么需要该 scope,再使用
gh auth refresh --scopes <scope>。 - 如果 rate limited 或 unauthorized,先确认 active 账号、host 和仓库访问权限;不要重试破坏性命令。
- 如果输出包含 secrets,回复前先脱敏。
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.
- 3d ago First seen · 63 lines · 109 tokens per session scan A c2a52011b502
github-cli is a skill published in the GitHub repository DongLiStudio/personal-agent-foundation (11 stars, last pushed 16d ago), licensed Apache-2.0. It adds 109 tokens to every session and 1,031 once invoked, about $0.0005 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
windows-mcp-tool-tester
Automated testing skill for Windows-MCP tools. Use this skill whenever the user wants to test, validate, benchmark, or evaluate any Windows-MCP tool (App, PowerShell, Screenshot, Snapshot, Click, Type, Scroll, Move, Shortcut, Wait, MultiSelect, MultiEdit, Clipboard, Process, Notification, FileSystem, Registry…
facts-discover
Scan the codebase and classify every fact by lifecycle stage — tag @draft, @spec, or @implemented based on what the code actually shows. Add missing facts, fix inaccurate ones, remove obsolete ones. Use when asked to discover facts, bootstrap or update a fact sheet, scan the codebase for truths, sync facts to match…
anneal
Use when the user wants to systematically fix AI code slop — duplicated logic, over-engineering, silent error swallowing, convention drift, cargo-cult patterns, and other LLM-introduced architectural decay — over a specified duration.
new-service
Add a new service to Harbor — scaffold the compose config, environment variables, metadata, documentation, and cross-service integrations. Use this skill whenever the user wants to add a new service to Harbor, integrate a new tool/app/model server, create a compose configuration for a new project, or onboard any…
harbor
CLI toolkit for managing containerized LLM services. Use when the user wants to start, stop, configure, or manage AI/LLM services like Ollama, Open WebUI, llama.cpp, vLLM, LiteLLM, ComfyUI, and 250+ others. Triggers on requests to "run a model", "start ollama", "set up an LLM", "configure harbor", "manage services"…
bughunt
Fully autonomous bug hunting pipeline — discover bugs in a scoped area using parallel subagents, independently triage each finding, fix confirmed issues with subagents, then audit all fixes against repo constraints and target platforms. Runs end-to-end without user interaction.