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 0fuk/OpenACCP --skill gh-backupgit clone --depth 1 https://github.com/0fuk/OpenACCPWrote 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/0fuk/openaccp/gh-backup)<a href="https://agentmods.dev/skills/0fuk/openaccp/gh-backup"><img src="https://agentmods.dev/badge/skills/0fuk/openaccp/gh-backup/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/0fuk/openaccp/gh-backup"><img src="https://agentmods.dev/badge/skills/0fuk/openaccp/gh-backup.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 | $0.00137 | $0.01188 |
| Opus 5.5 | $0.00055 | $0.00475 |
| Sonnet 5.5 | $0.00027 | $0.00238 |
| Haiku 4.5 | $0.00014 | $0.00119 |
Grade A, and why
gh-backup 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 2d 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.
What it actually says
/gh-backup — GitHub 同步与可信校验
一句话:推上去不算备份,从远端全新克隆下来逐文件对得上才算。 每次执行都以读数收尾,不以「已同步」三个字收尾。项目路径读项目根 PROJECT-PROFILE.md;下文路径以颐润(Yirun)新机为例。
备份面(四类,各有归宿)
| 类 | 归宿 | 怎么验 |
|---|---|---|
| 代码(主仓全部线分支、候选 / 生产标签) | 代码仓远端 github |
体检脚本:本地每个分支尖与标签都能在远端找到(ls-remote 回读相等) |
| 工作区(信箱与台账、工具脚本、全部技能、记忆、规则文件、产品资料文本) | 私有规范仓 | 镜像脚本:推送 → 全新克隆 → 按清单逐文件比 sha256 |
| 生产数据库 | 不进 GitHub(含客户数据);归服务器每晚备份 + 云盘快照 + 对象存储 | 看部署线巡检状态与最近一次恢复核对的日期 |
| 凭据(服务器密钥、库口令、会话凭条) | 不进 GitHub;owner 自存 | 只提醒,不触碰 |
步骤(固定顺序)
- 体检:跑
C:\VyqoAI\Yirun\tools\sync-check.ps1。「漂移」每一条都要处置:在飞施工线的本地领先 → 记下线名与预计交回时刻;其余立即推(普通推送)。「未提交」逐条判:未跟踪的临时件可留,其余查归属。 - 镜像:跑
C:\VyqoAI\Yirun\tools\vault-mirror.ps1(先-DryRun仅当范围或排除规则刚改过)。脚本自带:排除规则 → 清单MIRROR-MANIFEST.txt与排除清单MIRROR-EXCLUDED.txt→ 提交 → 推送 → 全新克隆逐文件校验。末行必须是VAULT_MIRROR_OK。 - 审清单(review):看本次新增的排除项是否合理(有没有该备份却被误排的重要文件,例如台账、判据、执行令);看有没有不该推的东西混进清单(抽 10 个)。误排的改名或脱敏后重跑;误推的立即从仓里删并报告 owner(已推内容视为已外泄,不靠删除补救)。
- 标签对齐:生产标签在代码仓与规范仓各打同名标签并推(规范仓标签 = 上线当刻的规则与规范快照)。
- 收尾读数(写进台账一行,格式固定):
代码仓:分支 a / 标签 b 全在远端,漂移 0(或列出在飞线)· 规范仓:提交 <sha>,已推 N / 校验一致 N / 排除 M · 库备份:最近一次 <时刻>,巡检 <状态>。
硬规矩
- 禁 force-push、禁改写历史;提交身份用仓内既定的集成身份,commit 零署名尾注。
- 不入库:口令、密钥、连接串、会话凭条、客户与员工个人信息(姓名、手机号、证件号)、截图与录像、数据表格与库转储。拿不准宁可排除并列入排除清单。
- 排除清单只写「路径 + 原因类别」,不写命中的具体内容。
- 新增一类要备份的目录 = 改镜像脚本的范围表 + 本技能的备份面表,两处同改。
- 校验失败(不一致 > 0 或末行非 OK)= 备份不可信,当场上报,不得带着失败过门或收工。
恢复演练(每月一次或换机时)
全新机器上:克隆代码仓与规范仓 → 按规范仓 PROJECT-PROFILE.md 重建工作区目录 → 技能与记忆拷回用户目录 → 向 owner 取凭据 → 跑体检脚本。把「缺了什么才跑不起来」写回本技能的备份面表。
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.
- 2d ago First seen · 34 lines · 137 tokens per session scan A bf8efc64d257
gh-backup is a skill published in the GitHub repository 0fuk/OpenACCP (2 stars, last pushed 2d ago), licensed MIT. It adds 137 tokens to every session and 1,188 once invoked, about $0.0005 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 2026-10-14.
Other skills, from other repositories
git-wrapup
Land working-tree changes as logical commits — the work grouped by concern, topped by a release commit (version bump, changelog, regenerated artifacts). The work commits land first, then the version bump, verification, and the release commit on top. Stops at "committed locally on main" — or, when the project releases…
release-and-publish
Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, fast-forwards main when the release rode a release PR, creates the annotated tag on the commit main now points at, pushes commits and tags, then publishes…
release-pr-review
Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
git-integration
Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.
aiwg-pr
AIWG-specific pull request delivery workflow for AIWG product/workspace changes; not the generic repository PR process.