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 rexleimo/aios --skill retrogit clone --depth 1 https://github.com/rexleimo/aiosWrote 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/rexleimo/aios/retro)<a href="https://agentmods.dev/skills/rexleimo/aios/retro"><img src="https://agentmods.dev/badge/skills/rexleimo/aios/retro/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/rexleimo/aios/retro"><img src="https://agentmods.dev/badge/skills/rexleimo/aios/retro.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 | $0.00067 | $0.01491 |
| Opus 5.5 | $0.00027 | $0.00596 |
| Sonnet 5.5 | $0.00013 | $0.00298 |
| Haiku 4.5 | $0.00007 | $0.00149 |
Grade A, and why
retro 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retro(会话复盘 → 环境改进候选)
复盘一次会话,产出的不是对代码的意见,而是对编码环境的改法:让下一轮同类任务更省、更少犯错。会话由用户指定,未指定则默认本次。
铁律:只提案,不改文件
- 本 skill 不写任何文件,不创建分支,不改 skill / 规则 / 配置。
- 每条候选落地走既有受控闭环:
aios skill propose→review --approve|--reject|--quarantine→apply→ 需要时rollback(scripts/lib/tooling/skills/skill-workshop.mjs)。不得新开第二条写入路径。 - 改动 rex-harness 的 skill 文本额外走 training gate(
aios skill certify)与子模块发布流;改 AGENTS.md / 检查脚本属主仓库改动。
第一步:读原始材料,不靠回忆
从确定性来源取证,而不是凭记忆复述会话:
- 本轮对话记录(当前会话的完整轮次);
- ContextDB 会话事件与
.aios/运行状态; git status/git diff/git log(本轮真实改了什么);docs/plans/、CHANGELOG、.aios/planning/账本(计划与证据实际落到哪);- 如上下文被压缩过,
refs read <ref_id>召回原工具输出。
每条候选必须给出源引用(文件:行、事件 id 或对话轮次)。给不出引用的候选一律不列——宁可少列,不得编造。
第二步:七类候选
每一类都有触发条件,会话里没发生就明确写"未见",不硬凑:
- 导航(Navigation) — agent 找文件/信息花了很久,或存在隐藏依赖?一条导航指针即可解决?当会话里出现长时间找不到信息时。
- 确定性检查(Automated checks) — agent 犯了本可被检查拦住的错?先读仓库自己的 check 命令(
package.json脚本、CI workflow、scripts/test-suites.json),已有但没接线或悄悄坏掉的检查算发现,不算重新发明。仓库没有任何护栏(无 pre-commit、也无 CI 跑 lint/typecheck/test)= 本身就是一条 finding。当错误本可被自动拦住,或仓库根本没有护栏时。 - 编码标准(Coding standards) — reviewer agent 该拿到新规则?既有规则该删/该澄清?先分类再给动作:机械违规(固定句法模式、禁用 API、import 形状、文件位置规则)一律降级成确定性检查——仓库 linter 自定义规则、pre-commit hook 或 CI job,能写检查就不写规则;
rex-engineering-standards/CODING_STANDARDS.md只留真正需要判断力的条目(跨文件一致性、"与周围风格一致"这类检查永远替代不了的)。标准文本的 owner 仍是rex-engineering-standards,本 skill 不新增第二个 owner。当 reviewer 漏掉了错时。 - AGENTS.md 增删 — 有 steering 指令该挪去标准或检查?文件是否过长?AGENTS.md 的用途是导航指针,塞进流程细节就是负资产。当 AGENTS.md 明显膨胀时。
- 工具经济性(Tool economy) — 昂贵/浪费的工具调用?哪个 CLI/MCP 输出特别吃 token(本仓库有
refs/ offload / RTK 压缩面可对照)?当出现昂贵工具调用时。 - 无效指令(No-ops) — steering 文件里存在不改变 agent 行为的指令(写了也不会被遵守、或与其它指令重复)。当 steering 文件臃肿时。
- 信息可达性(Information access) — 关键信息当时拿不到,本可以低成本拿到(tee 开发服务器日志、只读访问某服务)?当会话因缺信息而绕路时。
分配原则(写进候选的理由里)
- 上下文压力在实施侧:实施 agent 要做探索、写码、调试,review agent 只拿 diff、压力最小——所以标准由 review 侧施加,别往实施侧加规则。
- 标准、检查、导航指针三者的归属不混用:能机械判定的写成检查,需要判断力的写进标准,其余写成指针。
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 · 64 lines · 67 tokens per session scan A 3548d041d3fd
retro is a skill published in the GitHub repository rexleimo/aios (54 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 1,491 once invoked, about $0.0003 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 2026-10-16.
Other skills, from other repositories
apple-calendar
Read macOS Calendar events via the icalBuddy CLI and create events via AppleScript (osascript). Use to check the user's calendar, agenda, upcoming events, or add an event on macOS.
apple-reminders
Manage Apple Reminders via the remindctl CLI on macOS — list, add, complete, delete, manage lists.
gog-workspace
Use the gog CLI for Google Workspace tasks across Gmail, Calendar, Drive, Docs, Sheets, Contacts, and related services. Use when the user asks to check email, search Gmail, inspect calendar events, find Drive files, read Docs or Sheets, or manage Google Workspace data through gog.
apple-notes
Manage Apple Notes via the memo CLI on macOS — create, view, search, edit, export.
Agent Browser Automation
Fast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.
fast-resume
Search local coding-agent session history and identify safe resume commands. Use when the user asks to find, inspect, continue, or recover previous work from Claude Code, Codex, Pi, or another agent indexed by fast-resume.