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 skills add jianshuo/claude-skills --skill wjs-cleaning-spamgit clone --depth 1 https://github.com/jianshuo/claude-skillsWrote 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/jianshuo/claude-skills/wjs-cleaning-spam)<a href="https://agentmods.dev/skills/jianshuo/claude-skills/wjs-cleaning-spam"><img src="https://agentmods.dev/badge/skills/jianshuo/claude-skills/wjs-cleaning-spam/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jianshuo/claude-skills/wjs-cleaning-spam"><img src="https://agentmods.dev/badge/skills/jianshuo/claude-skills/wjs-cleaning-spam.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00116 | $0.01059 |
| Opus 5 | $0.00058 | $0.00530 |
| Sonnet 5 | $0.00023 | $0.00212 |
| Haiku 4.5 | $0.00012 | $0.00106 |
Grade A, and why
wjs-cleaning-spam 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 13d 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.
What it actually says
wjs-cleaning-spam
清理挂在王建硕推文下的同城引流 spam 回复：隐藏回复 + 静音账号。
Core Principle
别人的推文删不掉。 X 只给串主两个武器：hide reply（从评论区移除，访客不可见）和 mute（通知里不再出现）。block 端点已被 X 从 API 下线（v2 返回 code 34，v1.1 要更高访问级别），真要拉黑只能网页手动。「删掉spam」= 隐藏 + 静音，做到 API 上限。
先 dry-run，人审 borderline，再 apply。 启发式会把真人评论（"机器人🤖"、"저지능🤪"）和 spam 变体（"我在济源呀🌷" + 隐形字符）分错边。flagged 直接处理，borderline 必须 Claude 逐条看。
Workflow
# 1. dry-run：输出 flagged + borderline 两个名单（JSON）
python3 ~/.claude/skills/wjs-cleaning-spam/scripts/clean_spam.py
# 2. Claude 逐条审 borderline：引流号特征 = 名字带 💕🌸♥ 装饰 / 同城话术 /
# 文本夹隐形字符（U+034F 等）/ 纯 emoji。真人评论（哪怕是骂人）不动。
# 把 borderline 里确认是 spam 的 id 并入名单。
# 3. apply：隐藏 + 静音（默认只处理 flagged；审完 borderline 用 --ids 指定全集）
python3 ~/.claude/skills/wjs-cleaning-spam/scripts/clean_spam.py --apply
python3 ~/.claude/skills/wjs-cleaning-spam/scripts/clean_spam.py --apply --ids id1,id2,...
# 4. 撞 429 限流（hide 约 50 次/15 分钟）脚本会自动停 —— 15 分钟后重跑同一条命令，
# state/cleaned.jsonl 记录了已处理的 id，自动跳过、续跑。
向用户汇报：隐藏几条、失败几条（及原因）、静音几个号；提醒 block 需网页手动。
踩过的坑（2026-06-10 实战）
| 坑 | 现实 |
|---|---|
| raw 查询 401 Unauthorized | query 参数里的 : 必须 URL 编码（to%3Ajianshuo），不是 auth 问题，别去换 oauth1/oauth2 |
xurl block 报 code 34 |
block 端点已从 X API 移除（v2/v1.1 都不行），用 mute 替代，别反复试 |
| hide 报 "Invalid Request" | 该回复所在会话的根推文不是用户的（用户只是参与别人的串），串主才有权隐藏——记为 hide-failed，账号照样静音 |
| hide 报 429 | 限流约 50 次/15 分钟，等窗口刷新重跑脚本即可（状态文件保证幂等） |
| 纯文本 spam 漏网 | "我在济源呀" 这类同城话术靠隐形字符（U+034F/零宽符）混过滤器——脚本已检测，新变体出现时把特征加进 NAME_KW / INVISIBLE |
| 误伤真人 | emoji 启发式会扫进真人短评——这就是 borderline 名单存在的原因，必须人审 |
When NOT to use
- spam 超过 7 天：recent-search 接口只覆盖 7 天，更早的要用网页手动
- 用户要删自己发的推文：直接
xurl delete POST_ID - 用户要拉黑某个具体账号：API 做不到，告诉他网页操作（账号主页 ⋯ → Block）
State
state/cleaned.jsonl — 每条处理过的回复一行（id / author / status）。重跑跳过已处理；想重头来删掉此文件。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 56 lines · 116 tokens per session scan A c02374efeb5e
wjs-cleaning-spam is a skill published in the GitHub repository jianshuo/claude-skills (129 stars, last pushed 23d ago), licensed MIT. It adds 116 tokens to every session and 1,059 once invoked, about $0.0006 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
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
google-ads-audit
Google Ads account audit and business context setup. Use for account-health audits and business-context setup. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should I fix in my ads", or when the user is new to NotFair and hasn't run…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.