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/strzhao/autopilotWrote 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/strzhao/autopilot/verify-change)<a href="https://agentmods.dev/commands/strzhao/autopilot/verify-change"><img src="https://agentmods.dev/badge/commands/strzhao/autopilot/verify-change/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/strzhao/autopilot/verify-change"><img src="https://agentmods.dev/badge/commands/strzhao/autopilot/verify-change.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 | $0.00025 | $0.00336 |
| Opus 5.5 | $0.00010 | $0.00134 |
| Sonnet 5.5 | $0.00005 | $0.00067 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
verify-change 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
用 claude -p（独立 headless session）客观验证 autopilot 仓库当前改动（git diff / git status 识别）是否符合预期、是否带来破坏性变更。
三条约束（其余你自行决定）
-
缓存同步：claude skill 有缓存——claude -p 加载
~/.claude/plugins/cache/autopilot/autopilot/<最新版本>/，而改动在plugins/autopilot/源码。验证前必须把改动文件 cp 到缓存对应版本目录，否则 claude -p 跑旧版，整个验证无效。验证后确认「缓存=源码」。 -
客观不引导：claude -p 用中性方式触发（不暗示预期结果），你只读证据陈述事实——禁用「符合预期 / 应 PASS / 正确 / work」等判断词，结论留给人据证据下。
-
AI 自由设计验证：你根据改动目的，自行决定验证哪些场景、怎么用 claude -p 触发、怎么覆盖「符合预期」+「破坏性检查」两个维度。不限制方法。
输出
事实陈述：跑了什么、观察到什么。最后给结论。
$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 · 19 lines · 25 tokens per session scan A d6207183c33c
verify-change is a command published in the GitHub repository strzhao/autopilot (32 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 336 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 2026-08-30.
Other commands, from other repositories
release
Release manager for frontend and mobile. Writes App Store notes, user-facing changelog, flags stale docs and landing copy. Actions: notes | changelog | docs | sync.
merge
Finish a PR properly: every check green, every review addressed — human and bot — then merge and clean up.
pr
Prepare and open a pull request the senior way: gate, template, scrubbed, everything visible.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
status
The state of play, computed fresh: branch, dirty files, the active sprint, open work, index freshness.
worktree
Manage git worktrees for isolated feature development.