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 Lingtai-AI/lingtai --skill topology-and-apigit clone --depth 1 https://github.com/Lingtai-AI/lingtaiWrote 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/lingtai-ai/lingtai/topology-and-api)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/topology-and-api"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/topology-and-api/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/lingtai-ai/lingtai/topology-and-api"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/topology-and-api.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 | $0.00032 | $0.00760 |
| Opus 5 | $0.00016 | $0.00380 |
| Sonnet 5 | $0.00006 | $0.00152 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
portal-guide-topology-and-api 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 12d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Topology and API
This is a nested lingtai-portal-guide reference. It covers the on-disk topology tape, replay chunks, HTTP endpoints, and live network JSON shape.
topology.jsonl
Each line is a TapeFrame:
{
"t": 1744567890123,
"net": { "nodes": [...], "avatar_edges": [...], "contact_edges": [...], "mail_edges": [...], "stats": {...} }
}
t is milliseconds since epoch. net is the same Network object /api/network serves; Network response shape below is a representative example of its core fields.
Replay chunks
Historical data is stored as delta-encoded, keyframed, gzipped JSON chunks bucketed by hour under .lingtai/.portal/replay/chunks/. The manifest.json in that chunks directory lists all available chunks with their time ranges and frame counts.
API endpoints
All endpoints are served at http://localhost:<port>.
| Endpoint | Method | Response | Description |
|---|---|---|---|
/api/network |
GET | Network JSON |
Live network state (nodes, edges, stats) |
/api/topology |
GET | JSON array of TapeFrame |
Full topology tape (can be large) |
/api/topology/manifest |
GET | ReplayManifest JSON |
Chunk metadata for replay |
/api/topology/chunk?start=<hourMs> |
GET | Chunk JSON (optionally gzip-encoded when requested) | Frames for one hour-bucket start time |
/api/topology/progress |
GET | JSON object such as { "current": N, "total": M } (or {}) |
Reconstruction progress parsed from reconstruct.progress |
/api/topology/rebuild |
POST | ReplayManifest JSON |
Trigger tape reconstruction from source data and rewrite replay chunks |
Network response shape
{
"nodes": [
{
"address": "orchestrator",
"agent_name": "orchestrator",
"nickname": "小灵",
"state": "ACTIVE",
"alive": true,
"is_human": false,
"capabilities": ["avatar", "search"]
}
],
"avatar_edges": [
{"parent": "orchestrator", "child": "avatar-1", "child_name": "avatar-1"}
],
"contact_edges": [
{"owner": "orchestrator", "target": "human", "name": "human"}
],
"mail_edges": [
{"sender": "orchestrator", "recipient": "human", "count": 5}
],
"stats": {
"active": 2,
"idle": 1,
"stuck": 0,
"asleep": 0,
"suspended": 3,
"total_mails": 42
}
}
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.
- 12d ago First seen · 77 lines · 32 tokens per session scan A 4f0a6ac4f122
portal-guide-topology-and-api is a skill published in the GitHub repository Lingtai-AI/lingtai (677 stars, last pushed today), licensed Apache-2.0. It adds 32 tokens to every session and 760 once invoked, about $0.0002 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…