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 DongLiStudio/personal-agent-foundation --skill wechat-readonly-analystgit clone --depth 1 https://github.com/DongLiStudio/personal-agent-foundationWrote 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/donglistudio/personal-agent-foundation/wechat-readonly-analyst)<a href="https://agentmods.dev/skills/donglistudio/personal-agent-foundation/wechat-readonly-analyst"><img src="https://agentmods.dev/badge/skills/donglistudio/personal-agent-foundation/wechat-readonly-analyst/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/donglistudio/personal-agent-foundation/wechat-readonly-analyst"><img src="https://agentmods.dev/badge/skills/donglistudio/personal-agent-foundation/wechat-readonly-analyst.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 | $0.00094 | $0.00779 |
| Opus 5.5 | $0.00038 | $0.00312 |
| Sonnet 5.5 | $0.00019 | $0.00156 |
| Haiku 4.5 | $0.00009 | $0.00078 |
Grade A, and why
wechat-readonly-analyst 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 14d 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
微信只读分析与 Profile 管理
本 Skill 把“逻辑身份路由”和“本机敏感绑定”分开：GLOBAL 的 WECHAT_PROFILES.md 只记录非敏感 Profile；具体 db_storage 路径和经数据库页校验的密钥目录由当前 Windows 用户的 DPAPI 加密保存，换电脑后重新绑定并重新取钥。
固定边界
- 仅处理用户本人拥有或明确获授权访问的本机微信数据。
- 每次操作必须显式指定
--profile；不设默认 Profile，不按最近活跃账号自动猜测。 - 用户确认账号归属并绑定 Profile，即授予该 Profile 在本机的持续只读权限，包括对本机可用微信数据库内容进行查询和在当前 Agent/模型上下文中分析；后续具体查询请求无需重复授权，直到用户删除该 Profile。
- 首次取钥或经明确密钥/解密错误确认需要刷新时，凭绑定时的持续授权自动只读扫描当前微信进程内存，不再逐次询问。只接受能与该 Profile 已绑定数据库通过页校验的密钥；无法验证当前账号与绑定数据一致时停止并告知用户，绝不猜测账号或覆盖旧凭据。成功查询后再以 Windows DPAPI CurrentUser 加密更新凭据槽。普通输入/日期/聊天名错误不得误报为密钥失效。日常查询直接使用该凭据槽，微信无需在线或登录。
- 不写微信进程，不注入、不附加调试器、不修改客户端或权限，不关闭安全软件。
- 不发送或修改消息，不调用原始 CLI 绕过包装器，不输出密钥、wxid、数据库路径或原始数据库。
- 不设置隐私条数上限。大量查询按稳定性分页处理，直到覆盖用户指定范围；输出形式按用户目标选择明细、统计、摘要或报告。
- 用户指定需要图片、语音、视频或附件时可直接读取本机可用内容，无需另行重复授权；必须如实说明工具当前支持的媒体类型和未覆盖项。
路由
- 安装、换机恢复、Profile 新增/删除：读取 安装与 Profile 生命周期。
- 查询、搜索、统计或总结：读取 查询与隐私门禁。
- 生成 HTML 报告：先形成已脱敏 JSON，再读取 报告结构。
- 兼容失败：读取 Windows 兼容与故障处理；HMAC 校验不通过就停止，不猜密钥、不降级安全门禁。
最终回报
说明实际 Profile、读取的本机时间范围和数量、密钥来源（DPAPI 缓存或本次刷新）、媒体覆盖、临时目录清理状态及未覆盖内容。只能说“全部本机可用记录”，不得宣称覆盖服务器端、已删除、已过期或尚未下载的消息。
What ships with it
45 files 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.
- .gitignore 33 B
- agents/openai.yaml 316 B
- assets/wechat-cli/LICENSE 11 KB
- assets/wechat-cli/pyproject.toml 504 B
- assets/wechat-cli/wechat_cli/__init__.py 0 B runs code
- assets/wechat-cli/wechat_cli/commands/__init__.py 0 B runs code
- assets/wechat-cli/wechat_cli/commands/history.py 3.4 KB runs code
- assets/wechat-cli/wechat_cli/commands/init.py 2.3 KB runs code
- assets/wechat-cli/wechat_cli/commands/search.py 4.7 KB runs code
- assets/wechat-cli/wechat_cli/commands/sessions.py 2.9 KB runs code
- assets/wechat-cli/wechat_cli/commands/stats.py 3.0 KB runs code
- assets/wechat-cli/wechat_cli/core/__init__.py 0 B runs code
- assets/wechat-cli/wechat_cli/core/config.py 7.7 KB runs code
- assets/wechat-cli/wechat_cli/core/contacts.py 6.4 KB runs code
- assets/wechat-cli/wechat_cli/core/context.py 1.5 KB runs code
- assets/wechat-cli/wechat_cli/core/crypto.py 2.6 KB runs code
- assets/wechat-cli/wechat_cli/core/db_cache.py 3.3 KB runs code
- assets/wechat-cli/wechat_cli/core/key_utils.py 923 B runs code
- assets/wechat-cli/wechat_cli/core/messages.py 29 KB runs code
- assets/wechat-cli/wechat_cli/keys/__init__.py 808 B runs code
- assets/wechat-cli/wechat_cli/keys/common.py 6.5 KB runs code
- assets/wechat-cli/wechat_cli/keys/scanner_windows.py 11 KB runs code
- assets/wechat-cli/wechat_cli/main.py 1.9 KB runs code
- assets/wechat-cli/wechat_cli/output/__init__.py 0 B runs code
- assets/wechat-cli/wechat_cli/output/formatter.py 709 B runs code
- references/provenance.md 802 B
- references/query-and-privacy.md 3.0 KB
- references/report-schema.md 850 B
- references/setup-and-profiles.md 2.8 KB
- references/windows-compatibility.md 1.7 KB
- requirements.lock 670 B
- scripts/install.ps1 4.2 KB runs code
- scripts/profile_manager.py 2.9 KB runs code
- scripts/profile_store.py 11 KB runs code
- scripts/render_report.py 9.1 KB runs code
- scripts/wechat_readonly.py 14 KB runs code
- tests/test_hardening.py 11 KB runs code
- THIRD_PARTY_NOTICES.md 710 B
- wheelhouse/click-8.1.8-py3-none-any.whl 96 KB
- wheelhouse/colorama-0.4.6-py2.py3-none-any.whl 25 KB
- wheelhouse/packaging-26.3-py3-none-any.whl 127 KB
- wheelhouse/pycryptodome-3.23.0-cp37-abi3-win_amd64.whl 1757 KB
- wheelhouse/setuptools-84.0.0-py3-none-any.whl 799 KB
- wheelhouse/wheel-0.48.0-py3-none-any.whl 33 KB
- wheelhouse/zstandard-0.23.0-cp312-cp312-win_amd64.whl 484 KB
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.
- 14d ago Changed cf254340666c
- 15d ago First seen · 31 lines · 94 tokens per session scan A afce1aaab783
wechat-readonly-analyst is a skill published in the GitHub repository DongLiStudio/personal-agent-foundation (16 stars, last pushed yesterday), licensed Apache-2.0. It adds 94 tokens to every session and 779 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-01.
Other skills, from other repositories
harbor-daytona
Use Harbor's Daytona sandbox platform for computer use — creating sandboxes, taking screenshots, sending mouse/keyboard input, and building agent loops. Use when the user wants to interact with a GUI, automate a desktop, do computer use, control a browser visually, or run Claude computer use against a Daytona sandbox.
boost-modules
Skill "boost-modules" from av/harbor, covering harbor boost custom modules, module structure, quick reference, output methods and stream text to client.
token-usage
Nested swiss-knife reference for token usage, cost, cache, and tool-call/API-call reports. Use for model cost reports, cache rates, budget/burn analysis, and tools-per-API-call trends across LingTai logs.
composio
Build AI agents and apps with Composio - access 200+ external tools with Tool Router or direct execution.
security-arsenal
Security payloads, bypass tables, wordlists, gf pattern names, always-rejected bug list, and conditionally-valid-with-chain table. Use when you need specific payloads for XSS/SSRF/SQLi/XXE/NoSQLi/command injection/SSTI/IDOR/path-traversal/HTTP smuggling/WebSocket/MFA bypass, bypass techniques, or to check if a finding…
frontmcp-development
Use when building any FrontMCP server component other than a tool (for tools, use create-tool). Covers @Resource static resources and parameterized URI templates; @Prompt reusable prompts (RAG, multi-turn); @Provider singleton dependency-injection providers (database pools, API clients); @Agent autonomous LLM agents…