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-endpointgit 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-endpoint)<a href="https://agentmods.dev/skills/justhamade/triadjs/triad-endpoint"><img src="https://agentmods.dev/badge/skills/justhamade/triadjs/triad-endpoint/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-endpoint"><img src="https://agentmods.dev/badge/skills/justhamade/triadjs/triad-endpoint.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 | $0.02612 |
| Opus 5.5 | $0.00030 | $0.01045 |
| Sonnet 5.5 | $0.00015 | $0.00522 |
| Haiku 4.5 | $0.00007 | $0.00261 |
Grade A, and why
triad-endpoint 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Endpoints and routers
endpoint() signature
import { endpoint, scenario, t } from '@triadjs/core';
export const createPet = endpoint({
name: 'createPet', // operationId in OpenAPI — must be unique
method: 'POST', // 'GET' | 'POST' | 'PUT' | 'PATCH' | 'DELETE'
path: '/pets', // Express-style (/pets/:id)
summary: 'Create a new pet', // one-line human summary
description: 'Longer prose.', // optional, flows into OpenAPI
tags: ['Pets'], // used to group operations in OpenAPI
request: {
body: CreatePet,
params: { id: t.string() },
query: { limit: t.int32().default(20) },
// headers: { xRequestId: t.string().optional() },
},
beforeHandler: requireAuth, // optional — see §Auth below
responses: {
201: { schema: Pet, description: 'Created' },
401: { schema: ApiError, description: 'Missing or invalid token' },
409: { schema: ApiError, description: 'Duplicate' },
},
handler: async (ctx) => {
const pet = await ctx.services.petRepo.create({
ownerId: ctx.state.user.id, // typed state from beforeHandler
...ctx.body,
});
return ctx.respond[201](pet);
},
behaviors: [ /* scenarios — see triad-behaviors skill */ ],
});
Return value is a normalized Endpoint — pass it to router.add(...).
HandlerContext — what ctx contains
Everything on ctx is inferred from the request and responses declarations:
| Field | Type |
|---|---|
ctx.params |
Inferred from request.params (or {}) |
ctx.query |
Inferred from request.query |
ctx.body |
Inferred from request.body (or undefined) |
ctx.headers |
Inferred from request.headers |
ctx.services |
ServiceContainer (module-augment it — see triad-services skill) |
ctx.state |
Readonly<TBeforeState> — state produced by the endpoint's beforeHandler. {} when no hook is declared |
ctx.respond |
{ [status]: (data) => HandlerResponse } — only declared statuses are present |
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 · 263 lines · 74 tokens per session scan A aa01f2e0ebf6
triad-endpoint is a skill published in the GitHub repository justhamade/triadjs (24 stars, last pushed 6mo ago), licensed MIT. It adds 74 tokens to every session and 2,612 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-endpoint compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| triad-endpointjusthamade/triadjs | Skill | 24 | 6mo ago | MIT | A | 74 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | yesterday | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | today | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 529 | 3d ago | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 253 | today | MIT | A | 106 | Claude Code |