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 commands/ibigqiang/feedgrab/shipgit clone --depth 1 https://github.com/iBigQiang/feedgrabWrote 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/commands/ibigqiang/feedgrab/ship)<a href="https://agentmods.dev/commands/ibigqiang/feedgrab/ship"><img src="https://agentmods.dev/badge/commands/ibigqiang/feedgrab/ship.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 | $0.00000 | $0.00983 |
| Opus 5 | $0.00000 | $0.00491 |
| Sonnet 5 | $0.00000 | $0.00197 |
| Haiku 4.5 | $0.00000 | $0.00098 |
Grade A, and why
ship 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.
What it actually says
完成当前功能的收尾工作：优先使用 Git Bash 执行 D:\Git\bin\bash.exe ./scripts/ship.sh 做收尾检查；若 Git Bash 不可用，再回退执行 powershell -NoProfile -ExecutionPolicy Bypass -File .\scripts\ship.ps1。然后更新文档、提交代码、推送到 GitHub。
请按以下步骤执行：
1. 确认当前状态
运行 git status 和 git diff --stat 查看所有变更，确认功能已完成。
2. 更新 DEVLOG.md
在 DEVLOG.md 顶部（第一个 --- 分隔线之前）新增本次版本条目，格式：
## YYYY-MM-DD · vX.Y.Z · 功能标题
### 背景
为什么要做这个功能，解决什么问题。
### 方案决策
选择了什么技术方案，关键设计决策。
### 改动范围
| 文件 | 类型 | 改动 |
|------|------|------|
| `路径` | 新建/修改 | 说明 |
### 验证结果
测试了什么，结果如何。
### 状态：已完成 ✅
3. 更新 CLAUDE.md / AGENTS.md
同步更新 CLAUDE.md 中的项目信息，确保与最新代码一致：
- 当前版本号 — 更新"迭代历史摘要"表格，新增本次版本条目
- 核心架构 — 如有新增/删除文件，更新目录树
- 支持的平台 — 如有新平台或抓取方式变更，更新平台表格
- 关键设计决策 — 如有重要的新设计决策，补充说明
同步更新 AGENTS.md（Codex CLI 使用的项目指令副本）：
- AGENTS.md 与 CLAUDE.md 内容对齐，面向 Codex CLI / 其他非 Claude Code 的 AI 代理
- 更新策略：CLAUDE.md 改什么，AGENTS.md 跟着改什么（版本号、架构图、平台表、关键设计决策保持一致）
- 若 CLAUDE.md 有精简（删掉 DEVLOG 已覆盖的细节），AGENTS.md 同步精简
4. 更新 README.md
将新功能的使用说明同步到 README.md 的对应位置：
- 新命令 → CLI 示例区
- 新配置项 → 配置表格
- 新平台/功能 → 平台支持表格
- 新文件 → 架构图
同时更新 README_en.md（如果存在且内容对应）。
5. 更新 skills/ 技能包
本项目自身 skill 化的 5 个技能包位于 skills/ 目录，需要与最新 CLI 能力保持一致：
| 技能包 | 关注点 | 更新条件 |
|---|---|---|
skills/feedgrab/SKILL.md |
单条 URL 抓取 | 新增平台 / 新命令 / description 里平台清单过期 |
skills/feedgrab-batch/SKILL.md |
批量抓取 | 新增批量命令（x-so / xhs-so / mpweixin-zhuanji 等） |
skills/feedgrab-setup/SKILL.md |
安装配置 | 新增依赖 / 配置项 / 诊断命令 |
skills/analyzer/SKILL.md |
内容分析 | 分析输出模板或 LLM 参数变化时 |
skills/video/SKILL.md |
视频/播客摘要 | 新增播客平台（如 v0.17.0 的小宇宙/喜马拉雅）/ 字幕源 / Whisper 管线 |
同步要点：
- description 字段里的平台/能力清单必须反映实际支持（会被 skill 路由使用）
- Supported Platforms / Commands 表格要加上新平台和新命令
- Examples 章节补充新功能用法
- 本次迭代如果没有新增平台/命令，仍需快速扫一遍确认 description 不过期
6. 提交代码
将所有变更（包括文档更新）一起提交：
- 使用 conventional commit 格式（feat/fix/docs/chore）
- 提交信息用英文前缀 + 英文描述
7. 推送到 GitHub
git push origin main
推送完成后告知用户结果。
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 · 88 lines · 0 tokens per session scan A 9c4f473ff798
ship is a command published in the GitHub repository iBigQiang/feedgrab (603 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 983 tokens. 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 commands, from other repositories
end
Command "end" from mnott/PAI, covering pai end, synopsis, options and see also.
today
Log daily accomplishments, reflect on the day, and prep tomorrow.
recap
Time-windowed "where was I?" — git commits, session notes, and files touched in the last N hours or days. Use after stepping away for a few hours or days. Not for cold starts after a long absence (use /tools:brief) or live development checks (use /tools:status).
wrap-up
Cierre de sesión iAmasters OS. Genera daily summary, sincroniza skills, propone commit.
finish-work
Command "finish-work" from lihaoze123/cptracker, covering finish work, step 1: quality gate, step 2: remind user to commit and step 3: record session (after commit).
speckit.git.commit
Auto-commit changes after a Spec Kit command completes.