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 chenyujing1234-netizen/trueAI --skill trueaigit clone --depth 1 https://github.com/chenyujing1234-netizen/trueAIWrote 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/chenyujing1234-netizen/trueai/trueai)<a href="https://agentmods.dev/skills/chenyujing1234-netizen/trueai/trueai"><img src="https://agentmods.dev/badge/skills/chenyujing1234-netizen/trueai/trueai/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/chenyujing1234-netizen/trueai/trueai"><img src="https://agentmods.dev/badge/skills/chenyujing1234-netizen/trueai/trueai.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 | $0.00074 | $0.02230 |
| Opus 5 | $0.00037 | $0.01115 |
| Sonnet 5 | $0.00015 | $0.00446 |
| Haiku 4.5 | $0.00007 | $0.00223 |
Grade A, and why
trueai scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sG "$TRUEAI_API_BASE/api/search/chat" \ How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TrueAI Skill
Helps an agent (Claude / Cursor / Cline / ChatGPT / your own pipeline) recommend, look up and compare AI SaaS apps from the TrueAI 真选AI catalog without ever leaving the chat.
The catalog ships with rich structured fields documented in
ai_tool_schema.json — name, slug,
tagline, description, developer, form_factor, is_free,
pricing_info, five sub-scores (overall / usability / effect / price / speed), official_url, categories, audiences, optional
external_reviews, etc.
When to use this skill
Trigger it any time the user is doing one of the following:
- Asking for a recommendation by need. "我想做一份中文 PPT", "need a free AI to clean up my photos", "我刚开始学编程，要免费的 AI 工具".
- Asking about a specific app by name. "Cursor 的定价是多少？", "通义千问支持 API 吗？", "What is Genspark?".
- Asking about an app by URL. The user pastes
https://cursor.comand wants to know what it is. - Browsing / comparing inside a category. "Top 5 free AI coding tools", "列几个国内能直接用的图像生成工具".
Do not use this skill for non-AI products, general web search, news, or anything that doesn't map onto the TrueAI catalog.
Setup (one-time)
The skill talks to a running TrueAI backend. Pick a base URL:
# Public hosted endpoint (recommended — nothing to install):
export TRUEAI_API_BASE=https://www.shiflowai.cloud
# Local dev (if you're running the TrueAI repo yourself):
# export TRUEAI_API_BASE=http://localhost:8000
There are two equivalent ways to invoke the skill — pick whichever your agent supports best.
A. Native MCP (recommended if your agent speaks MCP)
The TrueAI backend exposes two MCP transports — pick whichever your client supports:
| Transport | URL | When to use |
|---|---|---|
| Streamable HTTP (recommended) | https://www.shiflowai.cloud/mcp |
Smithery, modern Claude Desktop / Cursor / Cline / Windsurf |
| SSE (legacy) | https://www.shiflowai.cloud/mcp-sse/sse |
Older MCP clients that haven't migrated yet |
What ships with it
4 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.
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.
- 8d ago First seen · 221 lines · 74 tokens per session scan A 84a62b16f280
trueai is a skill published in the GitHub repository chenyujing1234-netizen/trueAI (0 stars, last pushed 3mo ago), licensed MIT. It adds 74 tokens to every session and 2,230 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
omh-accessibility-audit
This is a Hermes-native accessibility-audit workflow skill.
omh-backend
This is a Hermes-native backend workflow skill.
omh-image-cards
This is a Hermes-native img-summary workflow skill.
omh-codebase-uml
This is a Hermes-native codebase-uml workflow skill.
omh-rust
This is a Hermes-native rust workflow skill.
ulw-context
This is a Hermes-native context workflow skill.