cheat-bump

cheat-bump is a skill for Claude Code, Codex from XBuilderLAB/cheat-on-content. It costs 135 tokens per session (6,757 once invoked), scanned A, original, MIT.

A workflow for changing a content-scoring rubric, meaning the rules and weights used to judge content. It supports either changing the rubric itself or recalculating only the performance buckets.

In plain words
What is it for?
Use it to propose new scoring dimensions or weights, rescore a calibration set, check ranking consistency, review changes across models, or update bucket boundaries.
Why use it?
It prevents scoring rules and result ranges from being changed casually by requiring recalculation and review for larger changes.

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-bump
Any agent
npx skills add XBuilderLAB/cheat-on-content --skill cheat-bump
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-bump

README.md
[![agentmods](https://agentmods.dev/badge/skills/xbuilderlab/cheat-on-content/cheat-bump.svg)](https://agentmods.dev/skills/xbuilderlab/cheat-on-content/cheat-bump)
Your own site
<a href="https://agentmods.dev/skills/xbuilderlab/cheat-on-content/cheat-bump"><img src="https://agentmods.dev/badge/skills/xbuilderlab/cheat-on-content/cheat-bump.svg" alt="Measured on agentmods" height="20"></a>
Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,757 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 $0.00135 $0.06757
Opus 5 $0.00068 $0.03379
Sonnet 5 $0.00027 $0.01351
Haiku 4.5 $0.00014 $0.00676

Measured 4d ago against content hash 037bace95a9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cheat-bump 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-bump/SKILL.md · 478 lines

How it starts

The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/cheat-bump — Rubric / Bucket 升级

两种模式:

模式 触发 做什么 验证强度
完整 rubric bump --propose "<新公式>" 改公式 / 维度 / 权重 5 步 + 跨模型审核(强制)
bucket-only 重校 --bucket-only 只重新派生 bucket 边界 数据自动派生,无审核

完整 rubric bump 严格遵守 shared-references/bump-validation-protocol.md 的 5 步。bucket-only 走轻量路径——见下方 Phase B。

Overview

入口:用户触发 /cheat-bump
  ↓
[Phase A0: 检测调用模式]
  ↓
  ├─ --bucket-only  →  [Phase B: 轻量 bucket 重校]
  └─ --propose      →  [Phase 0~6: 完整 rubric bump]

Phase A0: 调用模式分流(先做)

读用户参数:

  • --bucket-only → 走 Phase B(轻量重校)
  • --propose "<...>" → 走 Phase 0~8(完整 rubric bump)
  • 都没有 → 询问用户:"你想做什么?1) 调 rubric 公式 / 加减维度 → --propose;2) 只重新派生 bucket 边界 → --bucket-only"

如果用户说"我觉得 ER 太低了想调"→ 是 --propose 路径。 如果用户说"我账号长大了,bucket 不准了"→ 是 --bucket-only 路径。 两条路径不能混调——一次操作只做一种事。


完整 rubric bump 流程

[用户:升级 rubric --propose "ER×1.5→2.0,砍 NA,加 MS"]
  ↓
[Phase 0: 前置门槛检查]
  ↓
[Phase 1: 写出新公式完整方程]
  ↓
[Phase 2: 校准池全量重打分]
  ↓
[Phase 3: 计算排序一致性]
  ↓
[Phase 4: 跨模型独立审核(强制)]
  ↓
[Phase 5: 落地 + cleanup pass]
  ↓
[Phase 6: 更新所有校准样本的 prediction 文件底部追加 Re-scored 行]

Constants

  • READINESS_HEURISTIC
    • 默认参考:校准池 ≥ 5 样本 + 至少 1 个跨样本观察有 ≥3 样本支持
    • 但 Claude 可以提议 bump(即使样本少)如果观察信号特别强:
      • N=3 但出现完全推翻当前 rubric 假设的强反例(composite 8.5 vs 实绩 5w 这种 ≥3x 偏差)
      • 1 篇出现单点但极强的现象(如评论区出现 ≥2000 赞的单一模因)
    • Claude 也可以拒绝 bump(即使样本足)如果证据弱:
      • N=10 但观察都是低置信度的零碎 pattern,无清晰方向
      • 用户复盘时大量"随便看了下"的非严肃判断
    • 写在 prediction header 或 cheat-bump 输出时必说明:本次提议是 default-aligned 还是 judgment-driven,给用户审视依据
  • THRESHOLD = 0.8 — 新排序与实绩排序一致性阈值(4/5)。这条写死——bump 验证的统计刚性
  • CROSS_MODEL_AUDIT = true — 调外部 LLM 独立审核。false 仅用于离线
  • REQUIRE_CONFIRM = true — 落地前要求用户明确"yes, bump"

Inputs

必填 来源
--propose 文本 用户参数;缺失则询问
rubric_notes.md 用户项目根
predictions/*.md 全量 校准池数据
.cheat-state.json 状态

Workflow

Phase 0: 前置门槛检查

Read the full file on GitHub · 478 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 · 478 lines · 135 tokens per session scan A 037bace95a9d

Subscribe to this mod's changes

cheat-bump is a skill published in the GitHub repository XBuilderLAB/cheat-on-content (6,715 stars, last pushed 3d ago), licensed MIT. It adds 135 tokens to every session and 6,757 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.

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