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/friuns2/codex-mobile/upstream-sync-curatornpx skills add friuns2/codex-mobile --skill upstream-sync-curatorgit clone --depth 1 https://github.com/friuns2/codex-mobileWrote 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/friuns2/codex-mobile/upstream-sync-curator)<a href="https://agentmods.dev/skills/friuns2/codex-mobile/upstream-sync-curator"><img src="https://agentmods.dev/badge/skills/friuns2/codex-mobile/upstream-sync-curator.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 | $0.00113 | $0.01611 |
| Opus 5 | $0.00056 | $0.00805 |
| Sonnet 5 | $0.00023 | $0.00322 |
| Haiku 4.5 | $0.00011 | $0.00161 |
Grade A, and why
upstream-sync-curator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upstream Sync Curator
仅用于本仓库 nervmor/codexui 与上游 friuns2/codexUI 之间的选择性同步。
固定上游地址:
https://github.com/friuns2/codexUI.git
不要直接同步整个 upstream。 固定执行“两阶段”流程:先分析 upstream 提交与代码变更,按功能主题整理候选变更;再根据用户选中的功能主题做选择性引入。
触发条件
当用户提到以下意图时触发:
- upstream sync
- 同步源仓库
- 选择性合并 upstream
- 分析上游提交
- 挑功能合并
仅适用于本仓库及其 upstream friuns2/codexUI。
第 1 阶段:准备环境
- 检查主工作区是否干净。 如果主工作区不干净,先停止并让用户决定如何处理,不要把已有修改卷入 upstream 同步流程。
git status --short
- 检查
origin是否指向当前 forknervmor/codexui。
git remote -v
- 配置或校验
upstream,并强制使用 HTTPS 地址,不要使用 SSH。
git remote get-url upstream
git remote remove upstream
git remote add upstream https://github.com/friuns2/codexUI.git
- 创建带时间戳的临时分支和临时 worktree,避免污染主工作区。
ts="$(date +%Y%m%d-%H%M%S)"
tmp_branch="upstream-sync-${ts}"
tmp_dir="$(mktemp -d -t codexui-upstream-sync-XXXXXX)"
git worktree add -b "${tmp_branch}" "${tmp_dir}" main
- 后续所有
fetch、log、diff、cherry-pick、merge都只在临时 worktree 内执行。 不要在主工作区直接做任何 upstream 分析或引入操作。
第 2 阶段:分析 upstream 变更
- 在临时 worktree 中获取最新的
origin/main和upstream/main。
cd "${tmp_dir}"
git fetch origin main
git fetch upstream main
- 计算当前 fork 与 upstream 的
merge-base。
base_commit="$(git merge-base origin/main upstream/main)"
echo "${base_commit}"
- 列出
upstream-onlycommits,并按时间顺序和改动范围整理。
git log --reverse --no-merges --oneline "${base_commit}..upstream/main"
git diff --stat "${base_commit}..upstream/main"
- 按“功能主题”分组候选变更。每组至少输出以下内容:
- 功能主题名
- 涉及 commit 列表
- 主要改动文件或目录
- 风险等级
- 与当前 fork 可能冲突的区域
- 是否推荐引入
- 分析完成后,必须先向用户给出分组结果和建议。 在用户明确选择功能主题之前,不得直接合并全部 upstream,也不得提前进入实际引入步骤。
建议输出格式:
功能主题:<name>
commits:<sha1>, <sha2>, ...
范围:<files/dirs>
风险:低 / 中 / 高
冲突点:<areas>
建议:推荐引入 / 可选 / 暂不建议
第 3 阶段:选择性引入策略
默认粒度是“功能主题”,而不是“整支 upstream”。
- 首选实现方式:按主题对应的 commit 序列执行
cherry-pick。
git cherry-pick <commit-a> <commit-b> <commit-c>
- 如果某个主题跨多个零散 commit,但文件边界清晰,则退化为按文件或目录从
upstream/main引入。
What ships with it
1 file 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.
- 5d ago First seen · 185 lines · 113 tokens per session scan A 564b9856d7bd
upstream-sync-curator is a skill published in the GitHub repository friuns2/codex-mobile (892 stars, last pushed 3mo ago), licensed MIT. It adds 113 tokens to every session and 1,611 once invoked, about $0.0006 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
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
app-builder
Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use…
contacts
Manage contacts, communication channels, access control, and invite links.
assistant-migration
Migrate from ChatGPT, Claude, OpenClaw, Hermes, Manus, and other AI assistants into Vellum by inspecting their data exports, conversation archives, files, prompts, custom instructions, memory, saved memories, tools, GPTs, workflows, integrations, and relationships, then mapping as much as safely possible into Vellum…
guardian-verify-setup
Set up channel verification for phone, Telegram, Slack, Discord, or email channels via outbound verification flow.
schedule
Reminders, automations, and recurring page, dashboard, or status monitoring (cron, RRULE, or fire-at).