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.
git clone --depth 1 https://github.com/xcodethink/open-claude-code-skillsWrote 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/xcodethink/open-claude-code-skills/rollback)<a href="https://agentmods.dev/commands/xcodethink/open-claude-code-skills/rollback"><img src="https://agentmods.dev/badge/commands/xcodethink/open-claude-code-skills/rollback/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/commands/xcodethink/open-claude-code-skills/rollback"><img src="https://agentmods.dev/badge/commands/xcodethink/open-claude-code-skills/rollback.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 | $0.00020 | $0.00281 |
| Opus 5.5 | $0.00008 | $0.00112 |
| Sonnet 5.5 | $0.00004 | $0.00056 |
| Haiku 4.5 | $0.00002 | $0.00028 |
Grade A, and why
rollback 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 1mo 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
rollback — 紧急回滚
用户输入 /rollback $ARGUMENTS 触发 revert 优先的回滚流程。
立刻读取并完整加载:
~/.claude/prompts/lib/05-部署/紧急回滚.md
按其"行为契约"段严格执行:
- 禁止
git reset --hard(丢失目标 commit 后的所有代码) - 禁止
git push --force到 main(除非用户明确授权) - 用
git revert生成反向提交,不影响其他代码 - 多 commit 用
git revert --no-commit <oldest>^..<newest>合并为一个 revert,逐个确认 - 回滚后立即验证最新功能完好 + 跑测试
参数含修饰符 → 叠加对应文件。
核心契约:回滚是最后手段,先查日志找根因做最小修复,确认无法修复才回滚 + 用户批准。
参数: $ARGUMENTS
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.
- 1mo ago First seen · 25 lines · 0 tokens per session scan A 9754cd43baad
rollback is a command published in the GitHub repository xcodethink/open-claude-code-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 281 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
deploy-release
Prepare and verify a staged or production deployment with rollback and smoke checks.
update-changelog
Update CHANGELOG.md with new entry based on git diff.
ijfw-ship
Run the IJFW workflow Ship phase (Deep D6). Pre-flight, deploy, and close. Usage: /ijfw-ship.
update-infos-release
Update Claude Code releases tracking (guide + landing + version bump).
changelog
Generate a changelog entry from git commits since the last tag using conventional commit format.
changelog
View recent CHANGELOG entries.