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-statusnpx skills add XBuilderLAB/cheat-on-content --skill cheat-statusgit clone --depth 1 https://github.com/XBuilderLAB/cheat-on-contentWhat 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 | $0.00082 | $0.02804 |
| Opus 5 | $0.00041 | $0.01402 |
| Sonnet 5 | $0.00016 | $0.00561 |
| Haiku 4.5 | $0.00008 | $0.00280 |
Grade A, and why
cheat-status 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 3d 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-status — 97% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cheat-status — 状态看板
读 state file + 扫描用户项目 → 汇总当前进度 → 输出"今天该做什么"清单。
Overview
[用户:状态]
↓
[Phase 1: 读 .cheat-state.json + 扫文件系统]
↓
[Phase 2: 计算派生指标]
↓
[Phase 3: 检测建议触发器(升级 / bump / 清算)]
↓
[Phase 4: 输出看板]
Constants
- SQLITE_UPGRADE_THRESHOLD = 30 — calibration_samples 达到 N 时建议升 SQLite
- CLEANUP_LINE_THRESHOLD = 600 — rubric_notes.md 行数超 N 时建议清算
- STALE_PREDICTION_DAYS = 30 — in_progress prediction 超 N 天未发布提示清理
Inputs
| 来源 | 用途 |
|---|---|
.cheat-state.json |
主要状态 |
predictions/*.md |
校准样本数 / pending retros |
candidates.md |
候选池规模 |
rubric_notes.md |
行数 / 当前版本 |
.cheat-cache/usage.jsonl(如有) |
meta-logging 数据,用于"距上次 bump 多少次预测" |
Workflow
Phase 1: 读状态
state = read_json('.cheat-state.json')
if not state:
return "你还没初始化。请先跑 /cheat-init。"
predictions = glob('predictions/*.md')
candidates_count = parse_candidates_md_entries()
rubric_lines = wc -l rubric_notes.md
Phase 2: 派生指标
| 指标 | 算法 |
|---|---|
| Buffer 数 | len(state.shoots) |
| Buffer 颜色 | 按 cadence-protocol.md 派生:buffer_days = buffer_count × target_publish_cadence_days,<1 红 / 1-2 橙 / 3-5 绿 / >5 蓝。如 target_publish_cadence_days=null → 颜色禁用 |
| Confidence 等级 | 按 state-management.md confidence 表 派生:从 calibration_samples 整数派生 emoji + 标签 |
| 最早一拍至今天数 | now - state.shoots[0].shot_at,用于警告"拍了 N 天没发" |
| 校准样本数 | predictions 中含完整复盘段(实绩数据非空)的文件数 |
| 待复盘 | state.pending_retros 中已过 RETRO_WINDOW_DAYS 的 |
| 池大小 | candidates.md 中 tier!=skip 的 entry 数 |
| 上次 bump 至今几次预测 | predictions 中 published_at > state.last_bump_at 的数量 |
| 同向偏差队列 | state.consecutive_directional_errors |
| in_progress 陈旧度 | now - state.in_progress_session.started_at(如有) |
Phase 3: 检测建议触发器
按优先级(高→低)逐项检查:
- Buffer 颜色 = 🔴 红 → 第一行高优先级警戒:"buffer 已 0/1 篇,下个发布日可能断更——今天必须拍 ≥1 条。说'推荐选题'我只推 top 1 稳分(不推实验性)"
- Buffer 颜色 = 🔵 蓝 → 高优先级提示:"buffer 已 N 篇积压。暂停拍摄,先发存货 + 复盘。说'已发布 ...'我帮你出队"
- state.shoots 中最早一项 shot_at > 14 天 → "你有视频拍了 N 天还没发——议题时效流失风险,建议尽快发或弃稿"
- in_progress 陈旧 (>= STALE_PREDICTION_DAYS) → 高优先级提示"清理或 publish"
- 待复盘 ≥ 1 → 高优先级"今天该复盘 X 篇"
pool_status=none+calibration_samples=0+ 距 init >24h → "🌱 你 init 完已经 N 天但还没拍——是因为没选题吗?跑 /cheat-seed 5 分钟拿 5 个候选 + 5 个 draft" 高优先级- Claude 判断系统性偏差信号(不是死磕 ≥3 同向) → 提示"建议跑 /cheat-bump"
- 默认参考:连续 ≥3 次同向偏差
- 但 Claude 可以更早:1 次极端偏差(≥10x)或 2 次同向 + 评论区强反向证据
- 也可以更晚:3 次同向但每次幅度都 <25%(可能只是噪声)
- 提示时显式标注:"本次是 [default-aligned] / [judgment-driven]"
- calibration_samples 跨入新 confidence 等级(0→1, 2→3, 5→6, 10→11, 20→21)→ 提示"🎉 confidence 升级:<旧等级> → <新等级>。bucket 中枢精度从 ±X% 提到 ±Y%"。仅作通知,无任何用户必须确认的操作——所有 skill 都已经按 calibration_samples 自动调整
- calibration_samples 跨过 5 → "你的 rubric 形态可以第一次正式 bump 了。回顾 rubric_notes.md 看观察记录段是否有 ≥3 样本支持的 pattern → 跑 /cheat-bump"
- calibration_samples 跨过 10 → "可以跑 /cheat-bump --bucket-only --scheme percentile 让 bucket 边界改用 percentile(永远自洽)"
- calibration_samples 跨过 SQLITE_UPGRADE_THRESHOLD 且 data_layer=markdown → "建议跑 tools/md-to-sqlite.py"(planned — batch 3, not yet available)
- rubric_notes.md 行数 > CLEANUP_LINE_THRESHOLD → "建议清算观察段(手动或下次 bump 触发)"
- calibration_samples ≥ 5 + pool_status=none → "可以开始建立选题池了"
- calibration_samples ≥ 15 + pool_status=none → "强烈建议建池:/cheat-trends 或手动建 candidates.md"
- state.hooks_installed=false → "你的 immutability 是君子协定,建议跑 /cheat-init 装 hook"
- state.last_bump_self_audited=true → "上次 bump 是自审。建议配置 mcp__llm-chat__chat 后下次 bump 走外部审"
- state.rubric_form_mismatch=true → "你的 content_form 不是 opinion-video,用了内置观点 rubric。前几篇预测会更不准,下次 bump 时建议自行调整权重适配你的形态"
- state.benchmark_status=pending → "🎯 你 init 时答应等下找对标账号但还没找。跑 /cheat-learn-from 导入 ≥3 条对标视频,工具就有 anchor 了"
- state.benchmark_status=imported + Claude 判断用户数据信号已超过 benchmark → "📊 你的真实数据已经成为主信号,benchmark 影响淡出"
- 默认参考:calibration_samples ≥ 10
- 但 Claude 可以更早:N=5 但用户的 (打分, 实绩) 配对里出现 ≥3 条与 benchmark pattern 不一致的——说明你的账号已经走出对标的路径
- 也可以更晚:N=15 但用户的样本都很相似,没足够多样性 → benchmark 仍有信号价值
- 提示是通知不是 gate——benchmark.md 永远保留作 sanity check,cheat-seed 仍可读
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.
- 3d ago First seen · 163 lines · 82 tokens per session scan A b86f6ff45fe3
cheat-status is a skill published in the GitHub repository XBuilderLAB/cheat-on-content (6,715 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 2,804 once invoked, about $0.0004 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…