Cheat on Content is a workflow for content creators that records predictions and results for each post, reviews performance later, and updates the criteria used for future decisions. It is intended to make content planning and publishing an experiment that becomes more informed over time. The catalogue contains the skills that implement this workflow.
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-content/cheat-score-blindnpx skills add XBuilderLAB/cheat-on-content --skill cheat-score-blindgit clone --depth 1 https://github.com/XBuilderLAB/cheat-on-contentWrote 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-content/cheat-score-blind)<a href="https://agentmods.dev/skills/xbuilderlab/cheat-on-content/cheat-score-blind"><img src="https://agentmods.dev/badge/skills/xbuilderlab/cheat-on-content/cheat-score-blind.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 | $0.00153 | $0.03581 |
| Opus 5 | $0.00077 | $0.01791 |
| Sonnet 5 | $0.00031 | $0.00716 |
| Haiku 4.5 | $0.00015 | $0.00358 |
Grade A, and why
cheat-score-blind 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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cheat-score-blind — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cheat-score-blind — Channel B (blind scorer sub-agent)
⚠️ 这是子 agent，不是用户 skill。只能由
cheat-score/cheat-predict/cheat-bump通过 Task tool spawn。用户直接 trigger 没有意义——主对话已经被污染，调用 blind sub-agent 在主 context 里跑不构成隔离。
Why this exists（绝不可省的背景）
cheat-on-content 的 7/9 维打分原本 inline 在主对话——但主 Claude 已经看过：
- 用户对话历史（含偶然提到的播放数 / 评论 / 情绪）
- 已发布作品的实绩数据
- 历史
predictions/*.md含复盘段（严重污染） - 用户的赞美 / 抱怨 / 期待
inline 打分 = 被污染的"盲"预测。问题在 cheat-bump Phase 2 校准池重打时最严重：Claude 知道每条实绩才回追 TN/CC 分，rank 一致性可能 overfit 不是真信号。
channel B 的角色：用 Task tool 把打分动作丢进一个全新 context——这个 sub-agent 没看过主对话、没读过 state、没碰过 predictions/。它只看 script 全文 + rubric_notes.md，按 rubric 打分。
输出回传主对话后，主 Claude 自己对比、做最终决策。隔离的是打分这个动作的输入，不是决策权。
三 channel 模型
| Channel | 输入 | 用途 | 风险 |
|---|---|---|---|
| A = 主对话 | 全部上下文 | 跟用户交互、写 retro、决策 | 被实绩 / 用户态度污染 |
| B = blind sub-agent (this) | 只 script + rubric_notes.md | 给一份未受污染的打分作为 anchor | 仍是 Claude，RLHF prior 共享 |
C = 跨模型 audit (mcp__llm-chat__chat to qwen-max) |
校准池数据 + 新公式 | bump 终局 sanity check | RPM 限制、模型差异、单点 |
A 决策时把 B 当对照看 disagreement，不当真理。C 只在 bump 终局调一次。
Inputs（唯一被允许的输入）
| 必填 | 来源 | 说明 |
|---|---|---|
<script-path> |
主 Claude 通过 Task prompt 显式传入 | scripts/<id>.md 全文 |
<rubric-notes-path> |
同上 | 用户项目根 rubric_notes.md 当前 rubric 公式 + 维度定义 |
仅此两个文件可读。其他一切硬拒绝——见下方 "Hard refusals" 段。
禁止读取（hard list）
下面这些路径 / 模式 sub-agent 绝不能 Read —— 即使主 Claude 在 Task prompt 里手滑塞进来，也要拒绝并在 JSON 输出标对应 refusal 码：
| 路径模式 | 为什么禁 | refusal_code |
|---|---|---|
.cheat-state.json |
含 calibration_samples / pending_retros / last_published_at / shoots — 全是后视数据 | blocked_contaminated_input |
predictions/*.md |
含 ## 预测 段 + ## 复盘 段，复盘段就是实绩 |
blocked_contaminated_input |
videos/*/report.md |
T+3d 抓回的真实数据 | blocked_contaminated_input |
videos/*/script.md |
后改拍摄稿，复盘时被对照 | blocked_contaminated_input |
STATUS.md |
cheat-status 渲染的看板，含过去数据 | blocked_contaminated_input |
.cheat-cache/usage.jsonl |
行为 log | blocked_contaminated_input |
rubric-memo.md |
cheat-bump 升级 Memo 累积档案——含真实视频名 + 实绩 + 派生证据。这是 channel B 的最大泄漏入口（PR #11 实测复现） | blocked_rubric_memo |
audience.md |
cheat-persona 从复盘评论派生的受众画像——含评论证据 / 实绩信号。属 channel A creative 资产，进 blind 打分 = 实绩泄漏 | blocked_audience |
| 任何含"播放 / 阅读 / 点赞 / 评论数 / 转发 / w / 万 / k / M"的文件 | 直接污染 | blocked_contaminated_input |
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.
- 5d ago First seen · 214 lines · 153 tokens per session scan A 0ec332b8b6e7
cheat-score-blind is a skill published in the GitHub repository XBuilderLAB/cheat-on-content (6,749 stars, last pushed 4d ago), licensed MIT. It adds 153 tokens to every session and 3,581 once invoked, about $0.0008 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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.
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.
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…