cheat-retro

cheat-retro is a skill for Claude Code, Codex from XBuilderLAB/cheat-on-content. It costs 0 tokens per session (6,248 once invoked), scanned A, original, MIT.

A review step that collects a prediction's later results, compares them with the original forecast, and records lessons for future scoring rules. T+N means checking performance N days after the prediction.

In plain words
What is it for?
Use it to gather performance data, compare results with predictions, review supporting assumptions and comments, append a review, and suggest rule changes when a consistent error appears.
Why use it?
It shows whether the assumptions behind predictions were accurate and helps identify repeated bias without altering the original forecast.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/xbuilderlab/cheat-on-content/cheat-retro
Any agent
npx skills add XBuilderLAB/cheat-on-content --skill cheat-retro
Clone the repo
git clone --depth 1 https://github.com/XBuilderLAB/cheat-on-content

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for cheat-retro

README.md
[![agentmods](https://agentmods.dev/badge/skills/xbuilderlab/cheat-on-content/cheat-retro.svg)](https://agentmods.dev/skills/xbuilderlab/cheat-on-content/cheat-retro)
Your own site
<a href="https://agentmods.dev/skills/xbuilderlab/cheat-on-content/cheat-retro"><img src="https://agentmods.dev/badge/skills/xbuilderlab/cheat-on-content/cheat-retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,248 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.06248
Opus 5 $0.00000 $0.03124
Sonnet 5 $0.00000 $0.01250
Haiku 4.5 $0.00000 $0.00625

Measured 4d ago against content hash e4857a971fac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cheat-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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/cheat-retro/SKILL.md · 380 lines

How it starts

The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/cheat-retro — 数据回收与复盘

抓 T+N 天的实际表现 → 对比预测 → 提炼新观察 → 写入 rubric-memo.md。只追加 ## 复盘 段,绝不改预测段rubric_notes.md 是 blind 白名单,只能保存通用公式、维度定义和抽象规则,不能写入样本名、实绩、评论、链接或播放/阅读数。

Overview

[用户:复盘 predictions/2026-05-04_...]
  ↓
[Phase 0: 校验 immutability + 校验时间窗口]
  ↓
[Phase 1: 抓数据(manual paste 或 adapter)]
  ↓
[Phase 2: 写实绩段 + top 评论关键词]
  ↓
[Phase 3: 验证/推翻预测的各假设]
  ↓
[Phase 4: 提炼新观察]
  ↓
[Phase 5: 落盘(追加到 ## 复盘 段)]
  ↓
[Phase 6: 写入 rubric-memo.md 的"观察记录"段]
  ↓
[Phase 7: 检测是否触发 bump 候选 → 提示用户跑 /cheat-bump]

Constants

  • RETRO_WINDOW_DAYS = 3 — 默认 T+3d。短视频快平台可设 1,长文设 7
  • DATA_SOURCE = manual — manual: 用户粘数字;adapter: 调对应平台 adapter(需配置)
  • AUTO_PROPOSE_BUMP = true — Claude 判断是否系统性偏差时自动提议 /cheat-bump
    • 默认参考:连续 ≥3 次同向偏差(high/low)→ 提议
    • 但 Claude 可以更早提议:1 次极端偏差(如中枢 50w 实绩 5w 这种 ≥10x),即使没有"连续"也提议
    • 也可以更晚:3 次同向但每次偏差都很小(<25%),可能只是噪声不是系统性
  • TOP_COMMENTS_N = 20 — 抓 / 粘 top N 高赞评论

💡 调用时覆盖:/cheat-retro <file> — window: 7 — source: adapter

Inputs

必填 来源
<prediction-file><video-folder> 用户参数;缺失则从 .cheat-state.jsonpending_retros[0]
rubric_notes.md 用户项目根(只读,用于当前规则上下文;不得写入实绩观察)
rubric-memo.md 用户项目根(写入复盘观察、实绩证据、样本名与评论信号)
.cheat-state.json 状态文件

入参解析(同 cheat-predict 双形态接受)

用户给的可能是:

  • predictions/2026-05-04_<id>_<short>.md → 直接用这个 prediction 文件
  • videos/2026-05-04_<id>_<short>/ → 找对应的 prediction 文件(按 id 匹配)+ 把 report.md 写到该 video folder 里
  • 缺省 → 从 pending_retros[0] 取最早的

Workflow

Phase 0: 校验

  1. <prediction-file>,确认存在
  2. 识别有效预测段:扫所有 ## 预测... 段(可能含 ## 预测## 预测 v1## 预测 v2 等):
    • 最后一个## 预测 vN 作为本次校准的依据(v2 存在则用 v2;只有 v1 则用 v1;legacy 单段 ## 预测 直接用)
    • state.shoots 对应项的 v2_prediction_written 应与"是否存在 v2 段"一致——不一致则警告(state 与文件脱节)
  3. 校验 immutability:在内存 cache 住所有 ## 预测... 段的内容(用于 Phase 5 后核对——全部段不可改,不只是有效段)
  4. 校验文件 header 有 Published at → 没登记的不能复盘,提示用户先 /cheat-publish
  5. 校验时间窗口:今天 - published_at >= RETRO_WINDOW_DAYS。不够 → 提示"还差 X 天",询问用户是否仍坚持复盘(标 early_retro: true
  6. 校验已有复盘段是否已填——已填则询问"是补充还是修正?"
    • 补充 → 在已有复盘段下追加新子段,标日期
    • 修正预测段(用户错觉)→ 拒绝

Read the full file on GitHub · 380 lines

Changes

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.

  1. 4d ago First seen · 380 lines · 0 tokens per session scan A e4857a971fac

Subscribe to this mod's changes

cheat-retro is a skill published in the GitHub repository XBuilderLAB/cheat-on-content (6,749 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,248 tokens. 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens