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 justhamade/triadjs --skill triad-channelgit clone --depth 1 https://github.com/justhamade/triadjsWrote 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/justhamade/triadjs/triad-channel)<a href="https://agentmods.dev/skills/justhamade/triadjs/triad-channel"><img src="https://agentmods.dev/badge/skills/justhamade/triadjs/triad-channel/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/justhamade/triadjs/triad-channel"><img src="https://agentmods.dev/badge/skills/justhamade/triadjs/triad-channel.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 | $0.00066 | $0.01857 |
| Opus 5.5 | $0.00026 | $0.00743 |
| Sonnet 5.5 | $0.00013 | $0.00371 |
| Haiku 4.5 | $0.00007 | $0.00186 |
Grade A, and why
triad-channel 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 2mo 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Channels (WebSockets)
Channels are the real-time counterpart to endpoints. Same schema DSL, same behavior builder, same router. Currently supported by the Fastify adapter only. The AsyncAPI generator (@triadjs/asyncapi) produces asyncapi.yaml alongside openapi.yaml when the router has channels.
channel() signature
import { channel, t } from '@triadjs/core';
interface ChatRoomState {
userId: string;
userName: string;
roomId: string;
}
export const chatRoom = channel({
name: 'chatRoom',
path: '/ws/rooms/:roomId',
summary: 'Real-time chat room',
description: 'Bidirectional chat for a room',
tags: ['Chat'],
// Phantom witness for typed ctx.state — value is ignored, type is used
state: {} as ChatRoomState,
connection: {
params: { roomId: t.string().format('uuid') },
headers: {
'x-user-id': t.string().format('uuid'),
'x-user-name': t.string().minLength(1),
},
// query: optional, same shape
},
clientMessages: {
sendMessage: { schema: SendMessagePayload, description: 'Post a message' },
typing: { schema: TypingPayload, description: 'Typing state' },
},
serverMessages: {
message: { schema: ChatMessage, description: 'New message' },
typing: { schema: TypingIndicator, description: 'Typing indicator' },
presence: { schema: UserPresence, description: 'Join/leave' },
error: { schema: ChannelError, description: 'Error' },
},
onConnect: async (ctx) => {
if (!isValidRoom(ctx.params.roomId)) {
return ctx.reject(404, 'Room not found');
}
ctx.state.userId = ctx.headers['x-user-id'];
ctx.state.userName = ctx.headers['x-user-name'];
ctx.state.roomId = ctx.params.roomId;
ctx.broadcast.presence({
userId: ctx.state.userId,
userName: ctx.state.userName,
action: 'joined',
});
},
onDisconnect: async (ctx) => {
if (ctx.state.userId) {
ctx.broadcast.presence({ /* ... */ action: 'left' });
}
},
handlers: {
// One handler per clientMessage. Missing or extra keys = compile error.
sendMessage: async (ctx, data) => {
const message = await ctx.services.messageStore.create({ /* ... */ });
ctx.broadcast.message(message); // to everyone including sender
},
typing: async (ctx, data) => {
ctx.broadcastOthers.typing({ /* ... */ }); // to everyone EXCEPT sender
},
},
behaviors: [ /* channel behavior scenarios */ ],
});
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.
- 2mo ago First seen · 204 lines · 66 tokens per session scan A c2e144338877
triad-channel is a skill published in the GitHub repository justhamade/triadjs (24 stars, last pushed 6mo ago), licensed MIT. It adds 66 tokens to every session and 1,857 once invoked, about $0.0003 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 2026-08-30.
triad-channel compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| triad-channeljusthamade/triadjs | Skill | 24 | 6mo ago | MIT | A | 66 | Claude Code |
| stripe-projectse2b-dev/E2B | Skill | 15k | yesterday | Apache-2.0 | A | 51 | Claude Code, Codex |
| nestjs-expertJeffallan/claude-skills | Skill | 12k | 8d ago | MIT | A | 107 | Claude Code |
| chat-sdkvercel-labs/open-agents | Skill | 5.9k | 2mo ago | MIT | A | 191 | Claude Code, Codex |
| nestjsericrisco/rsc-harness | Skill | 529 | 3d ago | MIT | A | 81 | Claude Code, Codex |
| azure-web-pubsub-tsbenjaminasterA/antigravity-awesome-skills | Skill | 465 | yesterday | MIT | A | 51 | Claude Code, Codex |
| better-authsecondsky/claude-skills | Skill | 247 | 7d ago | MIT | A | 53 | Claude Code |