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 usetheokit/theokit --skill theokit-routesgit clone --depth 1 https://github.com/usetheokit/theokitWrote 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/usetheokit/theokit/theokit-routes)<a href="https://agentmods.dev/skills/usetheokit/theokit/theokit-routes"><img src="https://agentmods.dev/badge/skills/usetheokit/theokit/theokit-routes/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/usetheokit/theokit/theokit-routes"><img src="https://agentmods.dev/badge/skills/usetheokit/theokit/theokit-routes.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 | $0.00027 | $0.01102 |
| Opus 5.5 | $0.00011 | $0.00441 |
| Sonnet 5.5 | $0.00005 | $0.00220 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
theokit-routes 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 1mo 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TheoKit Routes
The route() builder
import { route } from 'theokit/server/define'
import { z } from 'zod'
// GET — no body, optional params/query
export const GET = route()
.policy('public') // who may call it — required
.params(z.object({ id: z.coerce.number() })) // URL params
.query(z.object({ page: z.coerce.number().optional() })) // query string
.handler(({ params, query }) => ({ id: params.id, page: query?.page }))
.build()
// POST — body validation + custom status
export const POST = route()
.policy(({ subject }) => subject !== null) // any authenticated caller
.body(
z.object({
title: z.string().min(3),
done: z.boolean().default(false),
}),
)
.status(201)
.handler(({ body }) => {
// body is fully typed from the Zod schema
return db.insert(tasks).values(body).returning().get()
})
.build()
The chain is .policy(), .params(), .query(), .body(), .status(), .response(),
.csrf(), .handler(), and .build() closes it. server/routes/health.ts in this project is a
working one — read it rather than this block if the two ever disagree.
.csrf(false) opts a single route out of CSRF enforcement. It is for endpoints that legitimately
receive third-party POSTs — a Stripe or WhatsApp webhook, an OAuth callback — which authenticate by
signature rather than by session. policy('public') answers a different question (may an
unauthenticated caller reach this) and does NOT lift the CSRF gate: without .csrf(false) a webhook
is refused CSRF_INVALID before its signature is ever checked.
policy — who may call this route
Required on every exported method. The scanner refuses a route file that omits it and names the file, so absence is a build error rather than a route silently open to everyone.
policy: 'public' // open, and said out loud
policy: ({ subject }) => subject !== null // any authenticated caller
policy: ({ subject, params }) => requireOwner(subject, ownerOf(params.id)) // this subject owns this record
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.
- 1mo ago Changed c4c15edbc1be
- 1mo ago First seen · 114 lines · 27 tokens per session scan A 8627688d53a8
theokit-routes is a skill published in the GitHub repository usetheokit/theokit (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,102 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 2026-08-31.
Other skills, from other repositories
continuum-tools-mcp
Connect MCP servers (Stdio/SSE/StreamableHTTP) to a Continuum agent, configure tool filtering, set up tool-context capture/injection (e.g. sessionid), and read run artifacts (UI widgets, structured tool data). Invoke when the user asks "connect MCP", "filesystem tool", "remote API tool", "auto-capture sessionid"…
api-interface-design
Use when designing public APIs, module boundaries, provider adapters, tool schemas, or data contracts.
APIDesignArchitect
Complete API design intelligence — REST, GraphQL, gRPC, webhooks, API versioning, authentication, rate limiting, API governance, and building APIs that developers love and never want to leave.
DeveloperExperienceOS
Complete developer experience intelligence — SDK design, documentation, onboarding, developer community, API ergonomics, CLI tooling, and building products that developers love and evangelize.
StartupCTO
Complete CTO intelligence for early-stage startups — tech stack decisions, architecture, team building, technical debt management, and scaling from 0 to 10M users.
senior-dev
Activates the SeniorDev agent for full-stack software engineering. Use this skill when you need production-ready code: Next.js 14 frontends, FastAPI backends, TypeScript strict-mode components, PostgreSQL schemas, Redis caching, authentication flows, or complete REST/GraphQL APIs. SeniorDev always outputs complete…