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 skills/xbuilderlab/cheat-on-skill/skill-plannpx skills add XBuilderLAB/cheat-on-skill --skill skill-plangit clone --depth 1 https://github.com/XBuilderLAB/cheat-on-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/xbuilderlab/cheat-on-skill/skill-plan)<a href="https://agentmods.dev/skills/xbuilderlab/cheat-on-skill/skill-plan"><img src="https://agentmods.dev/badge/skills/xbuilderlab/cheat-on-skill/skill-plan.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 | $0.00133 | $0.02397 |
| Opus 5 | $0.00067 | $0.01198 |
| Sonnet 5 | $0.00027 | $0.00479 |
| Haiku 4.5 | $0.00013 | $0.00240 |
Grade A, and why
skill-plan 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 4d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/skill-plan — 个性化学习策略（差距 → 路径 → 上岸）
把一个目标岗位变成"以你的起点 + 每周时间，几个月内能学到能投简历"的可执行学习计划。
前置检查
- 读
.skill-state.json找该岗位。若不在 candidate_roles 或可学性判定为 ❌ 劝退/⛔ 吃力，先提醒用户回 skill-scan 重选或确认，别硬做注定挫败的计划。 - 若该岗位牵涉付费培训/内推，先确认它过了
../../shared-references/anti-scam-rubric.md；命中红线先劝退。 - 读
../../shared-references/learnability-rubric.md（差距维度对齐）和role-tiers.md（起步动作按档位）。
学习策略必含 6 块
-
差距分析（最重要）：把目标岗位 JD 要求 − 用户已有能力 = 要补的清单，逐条列，标出哪些可迁移（已有，略学即可）、哪些要从头学。差距清单决定整个计划，别跳过。
-
分阶段学习路径：拆成 2–4 个阶段，每阶段有：
- 目标（学完能做什么，可验证）
- 具体内容 + 推荐资源类型（优先免费/低成本 + 边学边做；要推具体课程/资源时用 WebSearch 查当下真实可得的，加年份，别凭记忆给可能失效的链接）
- AI 加速点：这一阶段怎么用 AI 当私教 / 用 AI 编程 / 用 AI 出作品，把学习曲线压短（这是 AI 时代学习的题眼，别让"用 AI"停在口号）
- 时间盒（以用户每周 N 小时算，这阶段几周）
-
作品集清单：列 2–4 件能放进简历/能演示的作品（按档位：S0 工具熟练度作品；S1 旧技能 ×AI 重做；S2 GitHub 可跑项目；S3 解决本行业真实痛点的 demo）。作品比证书值钱——它证明你真能干。
-
求职时间线：第几周开始投简历、投哪些渠道、面试要准备什么。明确"不必等全学完才投"——边投边补。
-
止损线：满足什么条件该停下复盘或调整（例：投 30 份 0 面试 / 学了 X 周完全跟不上 / 出现反诈红线）。给转型留个清醒的退出判断。
-
诚实周期与预期：以用户每周时间算，几个月到能投、几个月可能拿 offer。明说这是真实投入不是速成，不画饼。
需要时用 WebSearch 查该岗位当下的真实学习路径/主流工具栈/招聘要求（加年份），别给过时方案。
落盘（含「预期」——这是日后复盘对账的起点）
写入前先用系统时间取当前时间：
date '+%Y-%m-%d %H:%M %Z %z'
所有报告和状态记录必须带具体时间与时区，跟用户系统时区走。内部记录可用 2026-06-26 22:06 CST +0800；用户报告展示为 2026-06-26 22:06（本机时区 + UTC 偏移，如 中国标准时间 CST，UTC+8）。不要写死成某个固定国家的时间。
把策略写入 .skill-state.json 的 active（chosen_id / started_at=今天 / learning_plan），该岗位 status 改为 learning。
同时写 active.prediction：预计每周投入小时、预计几个月到能投简历、作品集清单、止损线（recorded_at=今天日期，recorded_at_full=具体时间和时区）。
这份预期写完别改——日后复盘拿"实际"和它对账，才能看清计划准不准、要不要调。
报告与存档收尾
学习计划生成后，不要直接结束。先问用户：
"如果这版方向和计划没问题，我可以帮你存档，并生成一份完整报告。推荐形式是 Markdown 源文件 + 可选 Word 版：Markdown 方便后续迭代，Word 方便发送/打印。你要现在生成吗？"
默认不要把 Markdown/HTML 作为用户交付物。对普通用户来说，看到代码或标记语法会困惑。
若用户同意，生成两类内容：
- 内部归档：继续写入
.skill-state.json；必要时生成reports/internal/<YYYY-MM-DD>-<target-slug>.md作为 agent 可维护的结构化存档，但不要把它作为主交付给用户。 - 用户阅读版源稿：先生成
reports/<YYYY-MM-DD>-<中文标题>-用户版.txt，用自然语言写成外行人也能读懂的完整报告。不要包含 HTML/CSS/Markdown 语法，不要要求用户用浏览器打开。 报告正文必须写生成时间：YYYY-MM-DD HH:mm（本机时区名 缩写，UTC 偏移），跟用户系统时区走，不要只写日期、也不要写死某国时间。示例：生成时间：2026-06-26 22:06（中国标准时间 CST，UTC+8）。
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.
- 4d ago First seen · 100 lines · 133 tokens per session scan A 6e342bbf1f22
skill-plan is a skill published in the GitHub repository XBuilderLAB/cheat-on-skill (176 stars, last pushed 2mo ago), licensed MIT. It adds 133 tokens to every session and 2,397 once invoked, about $0.0007 per session on Opus 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
interview
Produce a tailored interview prep sheet (behavioral, technical, system design, company) from a job description and the user's resume.
interview-analysis
This skill should be used when the user asks to "/interview-analysis", "analyze my interview", "debrief my interview", "what did I miss in the interview", "review my interview transcript", or pastes a transcript / notes from a just-finished interview. Reads the transcript (pasted, from --from-file, or auto-pulled from…
case-practice
This skill should be used when the user asks for "/case-practice", "/pm-job-search:case-practice", "drill me on product cases", "practice PM case interviews", "MC case drill", or "test my case-interview recognition". Runs drill 1 of the case-practice methodology — a multiple-choice (MC) rapid-recognition drill that…
mock-lab
面向任意行业与职能岗位进行真实模拟或逐题训练，重点覆盖互联网产品、AI 产品、战略商分、数据分析、咨询及商业化等方向。先确认目标公司、岗位、可选 JD、轮次与运行方式，再组合通用协议、岗位 Playbook、题型、问题模式、领域视角和用户材料。产品经理及以产品判断为核心的复合岗位进行完整模拟时，严格贴合公司业务赛道和岗位性质，在 1 小时内动态覆盖自我介绍题、简历深挖题、行为动机题、工作职能题、开放业务题、产品实战题和费米估算题七类；顺序和权重按 JD、轮次与现场回答调整。普通面试一次一题，真实模拟结束后统一复盘，逐题训练则答完即诊断并重组专业答案。用户说“模拟面试”“面试陪练”“按这个公司和 JD 问我”“练 AI…
interview-coach
Use when the user has an upcoming interview, received an interview invitation, or wants to prepare for a specific role at a specific company.
mock-interviewer
Run a realistic, pressure-tested mock interview for a specific role, one question at a time, with honest feedback at the end. Use when the user wants interview practice, a mock interview, or to rehearse answers for an upcoming interview.