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 anneheartrecord/charles-skill --skill x-account-auditgit clone --depth 1 https://github.com/anneheartrecord/charles-skillWrote 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/anneheartrecord/charles-skill/x-account-audit)<a href="https://agentmods.dev/skills/anneheartrecord/charles-skill/x-account-audit"><img src="https://agentmods.dev/badge/skills/anneheartrecord/charles-skill/x-account-audit/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/anneheartrecord/charles-skill/x-account-audit"><img src="https://agentmods.dev/badge/skills/anneheartrecord/charles-skill/x-account-audit.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00182 | $0.01749 |
| Opus 5 | $0.00091 | $0.00874 |
| Sonnet 5 | $0.00036 | $0.00350 |
| Haiku 4.5 | $0.00018 | $0.00175 |
Grade A, and why
x-account-audit 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X 账号门面诊断
主页不是名片,是分流器:陌生人从一条帖子点进主页,10 秒内要么明白「这个人和我的问题有关」并关注/深入,要么划走。本 skill 逐项体检门面,每项给结论 + 改写稿。
第 1 步:收集材料
前置条件:X cookie(env X_AUTH_TOKEN/X_CT0,配置方法见仓库 README)。按优先级取材:
- cookie 自动拉取(默认):用同仓 x-content-review 的脚本拉主页信息(bio/显示名/头像与 banner/置顶帖全文与数据/粉丝关注比),并把头像和 banner 下载到本地:
python3 <仓库>/x-content-review/scripts/fetch_x_pulse.py --user <handle> \
--profile --download-media <数据目录>/media
返回的 local_media.avatar / local_media.banner 是本地图片路径。必须用 Read 工具实际打开这两张图看,再做视觉诊断——头像看缩略图辨识度、是否手绘/真人固定 IP;banner 看是否强化了 bio 那一句话(而不是重复能力清单或放风景图)、手机端文字是否可读。不要只凭 URL 猜,一定要看图。
2. cookie 不可用时,退化为让用户粘贴:bio 全文、置顶帖内容、头像与封面截图。
3. 若用户本地有运营手册/核心参考/media kit(常见于知识库运营目录),先读,诊断结论必须与其定位一致。
第 2 步:逐项诊断
2.1 Bio(权重最高)
三大死法检查(命中任何一条即不合格):
| 死法 | 症状 | 判断标准 |
|---|---|---|
| 简历压缩包 | 身份堆叠:「工程师 / 投资者 / 写作者」 | 只能被分类,不能被选择——读者说不出「什么情况下找他」 |
| 口号 | 「长期主义」「做时间的朋友」 | 听起来正确,想不出任何动作 |
| 能力清单 | 罗列会什么 | 别人买的不是工具箱,是结果 |
改写要求:套价值句模板「我帮____,在____的时候,解决____问题」或定稿句式「我帮____,解决____,让他能____」。一次写 10 版再删:删太大的、太虚的、没证据的。选最容易被复述的,不是最漂亮的。
验收(三个测试):复述测试(陌生人能否说出你帮谁解决什么)、场景测试(什么情况下会想到找你)、转介绍测试(能否被介绍成一句带场景的话)。改写稿要预演这三个测试。
2.2 主页分流器三件套
逐一检查,缺一即断:
- 一句清楚介绍(bio,见上)。
- 一条代表判断的置顶帖:置顶必须露出判断/证据(Start Here、代表作、反常识判断),不能是随手日常或纯转发。
- 一个能继续了解或购买的入口:个人站/GitHub/落地页链接。检查链接是否存在、是否指向「下一步动作」而非泛泛首页。
2.3 封面(banner)与头像
- 头像:辨识度检查——缩略图尺寸下能否一眼认出?是否与其他平台一致(跨平台同脸)?真人照/固定 IP 形象优于频繁更换。
- 封面:是主页最大的免费广告位。合格标准:强化 bio 的同一句话(视觉化价值主张或证据),而不是风景图/默认图/与定位无关的装饰。封面文字在手机端要可读。
- 显示名:名字 + 一个记忆点即可,不要把 bio 塞进显示名(关键词堆叠是机器味)。
2.4 辨识度与一致性
- 名字、头像、bio、置顶、高频内容类别,五者是否指向同一束光(反复照向同一个地方)?
- 内容抽查:最近 10 条原创是否服务「三个反复问题」;若发现明显漂移(如定位是判断型却大量新闻搬运),指出来。
- 关注结构:被关注数 : 关注数,健康账号被关注远多于关注;互关堆出来的关注列表会稀释定位信号。
2.5 证据盘点(信任层)
按五类清点主页可见证据:作品 / 过程 / 结果 / 反馈 / 判断。
- 结果证据用「从____到____」句式;反馈证据只收具体的,不收「很专业很有帮助」。
- 检查证据是否摆进了「看见路径」:陌生人第一次看见你 → 哪句话让他知道和他有关 → 主页看到什么证据 → 去哪看完整内容 → 有需求怎么找你。断在哪,先修哪。
第 3 步:输出报告
固定结构,落盘 Markdown(用户有运营目录则存那里,命名 X账号诊断-YYYY-MM-DD.md):
- 总评:一句话说清当前门面最大的断点(只说一个,最痛的那个)。
- 逐项打分表:bio / 置顶 / 入口 / 头像 / 封面 / 辨识度 / 证据,每项 ✅/⚠️/❌ + 一句依据。
- 改写稿:bio 给 3 版可直接替换的候选(标注各自取舍);置顶给内容方向建议;封面给文案 + 构图描述(可对接图像生成)。
- 修复顺序:按「看见路径」断点排优先级,最多 3 件事,每件可当天完成。
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.
- 11d ago First seen · 86 lines · 182 tokens per session scan A a6fee07cac59
x-account-audit is a skill published in the GitHub repository anneheartrecord/charles-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 182 tokens to every session and 1,749 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
agent-recall
Persistent compounding memory for AI agents. 5 default MCP tools: sessionstart, sessionend, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (sessionstart) and exhale (sessionend). Correction-first memory with decision trail tracking, watchfor warnings, palace rooms…
mykg
Run mykg knowledge-graph commands inside Claude Code from one slash command /mykg. The user describes intent in natural language (extract, append, sync, resume, approve, walkthrough, parse-docs, fetch-web, query); the skill parses intent, builds the right mykg CLI command from the live --help output, confirms, runs…
swarmvault
Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval, and MCP artifacts to disk from books, notes, transcripts, exports, datasets, slide decks, files, URLs, code, and…
engraph
Index and search document collections using hybrid semantic + graph + full-text search. Use when users need to search knowledge bases, find connections between documents, discover related content via link graphs, or query indexed markdown collections.
compiler
Scans knowledge/, analyzes documents, generates summaries/concepts/connections to wiki/ with reference graph. Updates existing articles instead of creating duplicates.
linker
Discovers missing cross-domain connections between knowledge documents and creates/updates connection wiki articles.