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 yusenthebot/stanford-ai-agent-skill --skill skillgit clone --depth 1 https://github.com/yusenthebot/stanford-ai-agent-skillWrote 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/yusenthebot/stanford-ai-agent-skill/skill)<a href="https://agentmods.dev/skills/yusenthebot/stanford-ai-agent-skill/skill"><img src="https://agentmods.dev/badge/skills/yusenthebot/stanford-ai-agent-skill/skill/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/yusenthebot/stanford-ai-agent-skill/skill"><img src="https://agentmods.dev/badge/skills/yusenthebot/stanford-ai-agent-skill/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00134 | $0.01719 |
| Opus 5.5 | $0.00054 | $0.00688 |
| Sonnet 5.5 | $0.00027 | $0.00344 |
| Haiku 4.5 | $0.00013 | $0.00172 |
Grade A, and why
stanford-ai-agent-skill 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stanford AI Agent Skill
把 Stanford CS329A《Self-Improving AI Agents》的稳定方法，作为一个可选择性加载的双语合集使用。这个入口负责判断当前问题属于哪种决策，再读取对应 reference；不要把 7 个模块一次性全部塞入上下文。
Use the stable methods from Stanford CS329A, Self-Improving AI Agents, as one selectively loaded bilingual collection. Identify the decision, then read the matching reference. Never load all seven modules by default.
语言路由 / Language routing
- 用户主要用中文提问时，读取
references/下的中文模块并用中文回答。 - When the user asks mainly in English, read the matching file under
references/en/and answer in English. - If the prompt is mixed, follow the explicitly requested output language. Otherwise use the language of the decision question.
- 术语、代码、命令、文件名、指标名和课程英文引文保持原样，不要为了翻译改写技术标识。
使用流程
- 用一句话写出当前要做的决策，不是宽泛主题。
- 按路由表选择一个主模块；只有决策确实跨界时才加载第二个模块。
- 读取对应 reference，并严格执行其中的 E（Execution）与 B（Boundary）。
- 输出决策、证据、风险、判停条件和下一步；引用课程依据时附官方视频与时间戳。
- 涉及部署权限、训练数据回写或不可逆外部动作时，不因 benchmark 提升自动放行。
English equivalent: state the decision in one sentence; choose one primary module and at most one secondary module when genuinely needed; execute its E steps and respect its B boundaries; return the decision, evidence, risks, stop conditions, and next action; never use a benchmark gain alone to authorize deployment, training-data writeback, or irreversible external action.
路由表
| 当前决策 | 加载 reference |
|---|---|
| 这是不是一个 agent？最小闭环缺了什么？ | 01-agent-minimum-loop.md |
| 推理时预算应该花在采样、修订、检索还是验证？ | 02-verification-constrained-inference-budget.md |
| reward、verifier 或 LLM-as-judge 是否可信？ | 03-verification-signal-and-judge-audit.md |
| 多步任务如何处理依赖、并行、回滚和副作用？ | 04-dependency-reversibility-execution-control.md |
| 生成轨迹是否应该进入 SFT/RL？ | 05-verified-trajectory-training-gate.md |
| 缺失证据如何驱动检索、抽取、综合与引用？ | 06-evidence-gap-research.md |
| agent 是否达到某一部署范围或权限级别？ | 07-agent-production-readiness-eval.md |
What ships with it
19 files 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.
- INDEX.en.md 2.2 KB
- INDEX.md 2.2 KB
- references/01-agent-minimum-loop.md 8.4 KB
- references/02-verification-constrained-inference-budget.md 9.0 KB
- references/03-verification-signal-and-judge-audit.md 7.0 KB
- references/04-dependency-reversibility-execution-control.md 7.0 KB
- references/05-verified-trajectory-training-gate.md 7.7 KB
- references/06-evidence-gap-research.md 12 KB
- references/07-agent-production-readiness-eval.md 13 KB
- references/en/01-agent-minimum-loop.md 4.7 KB
- references/en/02-verification-constrained-inference-budget.md 4.7 KB
- references/en/03-verification-signal-and-judge-audit.md 4.2 KB
- references/en/04-dependency-reversibility-execution-control.md 4.6 KB
- references/en/05-verified-trajectory-training-gate.md 4.9 KB
- references/en/06-evidence-gap-research.md 4.8 KB
- references/en/07-agent-production-readiness-eval.md 5.2 KB
- tests/test-prompts.json 9.4 KB
- tests/test-results.en.md 2.1 KB
- tests/test-results.md 3.0 KB
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 · 90 lines · 134 tokens per session scan A 9ddf976901f4
stanford-ai-agent-skill is a skill published in the GitHub repository yusenthebot/stanford-ai-agent-skill (30 stars, last pushed 2mo ago), licensed MIT. It adds 134 tokens to every session and 1,719 once invoked, about $0.0005 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 skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.