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.
git 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/commands/justhamade/triadjs/new)<a href="https://agentmods.dev/commands/justhamade/triadjs/new"><img src="https://agentmods.dev/badge/commands/justhamade/triadjs/new/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/commands/justhamade/triadjs/new"><img src="https://agentmods.dev/badge/commands/justhamade/triadjs/new.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 | $0.00030 | $0.00955 |
| Opus 5.5 | $0.00012 | $0.00382 |
| Sonnet 5.5 | $0.00006 | $0.00191 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
new scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Load the using-triadjs skill for framework context, then the triad-schema, triad-endpoint, triad-services, triad-adapters, and triad-testing sub-skills as needed.
Scaffold a complete, working TriadJS project based on the user's description ($ARGUMENTS). Do NOT ask a stream of clarifying questions — pick sensible defaults (sqlite + Fastify + ESM + TypeScript + tsx for dev) and proceed. If the user's description is vague, scaffold a generic "Items" CRUD API as a starting point.
What to produce
Create this directory layout inside a subdirectory (or the current directory if empty):
package.json
tsconfig.json
triad.config.ts
src/
schemas/
<resource>.ts # t.model + CreateX/UpdateX derivations + ApiError
endpoints/
<resource>.ts # createX, getX, listX, updateX, deleteX with behaviors
repositories/
<resource>.ts # in-memory repo as a starting point
services.ts # createServices + declare module augmentation
test-setup.ts # default-exported test services factory
app.ts # createRouter + router.context with bounded context
server.ts # Fastify wiring
Mandatory rules
- Default-export the router from
src/app.ts. - Module-augment
ServiceContainerinsrc/services.ts—declare module '@triadjs/core' { interface ServiceContainer extends AppServices {} }. - Every endpoint has at least one behavior scenario, plus
...scenario.auto()in the behaviors array for boundary coverage. - Use
t.empty()for 204 responses, nevert.unknown().optional(). - Use
ctx.respond[status](body)exclusively — never raw{ status, body }. - Assertion strings use double quotes, match phrases from the
triad-behaviorsskill phrase table, and don't try to usenull. ApiErrormodel is shared across every endpoint's 4xx responses.- Pin
@triadjs/*packages to^0.2.0inpackage.jsonunless the user specifies otherwise. Before writing the finalpackage.json, runnpm view @triadjs/core versionto confirm the current published major/minor and adjust the range to match — the plugin version may drift ahead of what's on npm. - Enable Swagger UI in the generated
server.tsby passingdocs: truetotriadPlugin(Fastify),createTriadRouter(Express), orcreateTriadApp(Hono). This serves the live OpenAPI spec at/api-docs/openapi.jsonand Swagger UI at/api-docsas soon asnpm run devis running — no extra step needed. Default is "on in dev, off in production";docs: trueforces on in both.
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 · 66 lines · 30 tokens per session scan A 4e80faef75c5
new is a command published in the GitHub repository justhamade/triadjs (24 stars, last pushed 6mo ago), licensed MIT. It adds 30 tokens to every session and 955 once invoked, about $0.0001 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.
new compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| newjusthamade/triadjs | Command | 24 | 6mo ago | MIT | A | 30 | Claude Code |
| initfcakyon/claude-codex-settings | Command | 1.2k | today | Apache-2.0 | A | 0 | Claude Code |
| http-serviceMadAppGang/magus | Command | 14 | today | MIT | A | 27 | Claude Code |
| buildAzure/ai-gateway | Command | 5 | 11d ago | MIT | A | 0 | Claude Code |
| api-contract-reviewMozurok/fhorja.dev | Command | 10 | 29d ago | MIT | A | 64 | Claude Code |
| start-10-1minicoohei/ai-agent-camp | Command | 347 | 1mo ago | none | A | 2 | Claude Code |
| fastapimfmezger/ai_agent_dotfiles | Command | 7 | 3mo ago | MIT | A | 84 | Claude Code, Gemini CLI |