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-schemagit 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-schema)<a href="https://agentmods.dev/skills/justhamade/triadjs/triad-schema"><img src="https://agentmods.dev/badge/skills/justhamade/triadjs/triad-schema/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-schema"><img src="https://agentmods.dev/badge/skills/justhamade/triadjs/triad-schema.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 | $0.00108 | $0.02210 |
| Opus 5.5 | $0.00043 | $0.00884 |
| Sonnet 5.5 | $0.00022 | $0.00442 |
| Haiku 4.5 | $0.00011 | $0.00221 |
Grade A, and why
triad-schema 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Schema DSL — the t namespace
Every schema builder is a subclass of SchemaNode<TOutput>. Chainable methods return new instances; schemas are immutable. Import the namespace:
import { t } from '@triadjs/core';
Base metadata methods (on every schema)
| Method | Purpose |
|---|---|
.doc(description) |
Human description (→ OpenAPI description) |
.example(value) |
Example value for docs |
.deprecated(flag?) |
Mark deprecated |
.default(value) |
Default value — removes field from required[] and applies when undefined |
.optional() |
Field may be undefined — output type becomes T | undefined |
.nullable() |
Value may be null — output type becomes T | null |
.identity(flag?) |
DDD identity marker (emits x-triad-identity in OpenAPI) |
.storage(meta) |
Persistence hints consumed by @triadjs/drizzle — see the triad-drizzle skill |
Runtime methods: .validate(data) (→ { success, data } \| { success, errors }), .parse(data) (throws ValidationException), .toOpenAPI(ctx?).
Type inference:
type Pet = t.infer<typeof Pet>;
Primitives
Strings
const email = t.string().format('email').minLength(3).maxLength(255);
const uuid = t.string().format('uuid');
const slug = t.string().pattern(/^[a-z0-9-]+$/).minLength(1);
Constraints: .minLength(n), .maxLength(n), .pattern(regex), .format(fmt).
Valid formats: 'uuid' | 'email' | 'uri' | 'url' | 'hostname' | 'ipv4' | 'ipv6' | 'date' | 'date-time' | 'time' | 'duration' | 'byte' | 'binary' | 'password' | 'regex'.
Prefer
t.datetime()overt.string().format('date-time')— semantically clearer, identical OpenAPI output.
Numbers
const age = t.int32().min(0).max(120);
const price = t.float64().min(0).multipleOf(0.01);
const bigId = t.int64();
Constraints: .min(n), .max(n), .exclusiveMin(n), .exclusiveMax(n), .multipleOf(n).
int32— enforces-2^31..2^31-1,Number.isIntegerint64— enforcesNumber.isSafeInteger(±2^53)float32/float64— require finite numbers
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 · 198 lines · 108 tokens per session scan A 6223bca32e33
triad-schema is a skill published in the GitHub repository justhamade/triadjs (24 stars, last pushed 6mo ago), licensed MIT. It adds 108 tokens to every session and 2,210 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 2026-08-30.
triad-schema compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| triad-schemajusthamade/triadjs | Skill | 24 | 6mo ago | MIT | A | 108 | 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 |