tuturuuu-external-apps

tuturuuu-external-apps is a skill for Codex from tutur3u/platform. It costs 34 tokens per session (851 once invoked), scanned A, original, Apache-2.0.

Integration guidance for branded apps that connect to Tuturuuu through app tokens, APIs, file storage, content delivery, and administrator sessions.

In plain words
What is it for?
Use it to build an external app's authentication, API routes, uploads, content readers, publishing flow, and operational error reporting.
Why use it?
It helps keep secrets out of browsers and prevents mismatches between the external app and the Tuturuuu platform when exchanging data or publishing content.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 plugins/tuturuuu/scripts/validate_plugin.py.

Good fit Use it to build an external app's authentication, API routes, uploads, content readers, publishing flow, and operational error reporting.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/tutur3u/platform
agentmods
npx agentmods add skills/tutur3u/platform/tuturuuu-external-apps

Made for: Codex.

Wrote 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.

agentmods badge for tuturuuu-external-apps

README.md
[![agentmods](https://agentmods.dev/badge/skills/tutur3u/platform/tuturuuu-external-apps/github.svg)](https://agentmods.dev/skills/tutur3u/platform/tuturuuu-external-apps)
Your own site
<a href="https://agentmods.dev/skills/tutur3u/platform/tuturuuu-external-apps"><img src="https://agentmods.dev/badge/skills/tutur3u/platform/tuturuuu-external-apps/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.

agentmods 80×15 button for tuturuuu-external-apps

Your own site · 80×15
<a href="https://agentmods.dev/skills/tutur3u/platform/tuturuuu-external-apps"><img src="https://agentmods.dev/badge/skills/tutur3u/platform/tuturuuu-external-apps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 851 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.00851
Opus 5 $0.00017 $0.00426
Sonnet 5 $0.00007 $0.00170
Haiku 4.5 $0.00003 $0.00085

Measured yesterday against content hash a1b9b90250c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

tuturuuu-external-apps 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 yesterday.

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.

plugins/tuturuuu/skills/tuturuuu-external-apps/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tuturuuu External Apps

Core Workflow

Use this skill for external or branded apps that connect back to Tuturuuu instead of living inside apps/web, especially sites with their own admin surface, storage, content delivery, or publishing flow.

Start with AGENTS.md, git status --short, and active coordination notes. Then map both sides of the integration:

  • the external app's auth/session, admin API routes, storage routes, and public content readers
  • the Tuturuuu control-plane routes under apps/web/src/app/api/v1/auth and apps/web/src/app/api/v1/workspaces/[wsId], including external projects, member access, roles, and Drive storage
  • the external app manifest/schema and any read* model normalizers that convert entries, blocks, assets, profile data, and metadata into app content

Read references/external-app-patterns.md when implementing auth exchange, invitation decisions, member or role management, Drive browsing, direct uploads, publish/delivery behavior, or error reporting.

Integration Rules

  • Keep app secrets server-only. Browsers call the external app's own API routes; those routes exchange or refresh Tuturuuu app tokens and attach bearer tokens to Tuturuuu API requests.
  • Persist admin sessions in encrypted HttpOnly cookies with access-token and refresh-token expiries. Add proactive refresh and retry-on-401 behavior so long-lived admin pages do not fall into stale-token Unauthorized states.
  • Reauthorize refresh requests against the linked workspace and requested external-project scopes. Refresh tokens must not carry normal external-projects:*, read, manage, or publish bearer scopes.
  • Treat a pending linked-workspace invitation as a first-class sign-in state. Let the user accept or decline inside the external app through Tuturuuu's single-use invitation-action exchange; never send them away to find the invitation manually. Keep the action token server-only in a short-lived, encrypted HttpOnly cookie and protect decisions with same-origin and CSRF checks.
  • Include member, invitation, role, and Drive management when the external app has an authenticated admin surface and the registration grants those scopes. Use external-app-aware workspace APIs; do not fall back to browser Supabase sessions or standard dashboard-only routes that reject valid app sessions.
  • Keep file bytes out of app API routes. Request signed upload metadata through the app API, upload directly from the browser to the signed URL, then save only the returned storage path and file metadata with the entry or asset mutation.
  • Reject accidental File/audioFile/raw multipart uploads in metadata save routes with a clear 400.
  • Save delivery-facing status and metadata through the entry or asset payload. Do not call extra publish endpoints unless the public delivery path truly consumes publish-event snapshots rather than current entry state.
  • Show admin progress by explicit step and percentage. Report sanitized status, step, short message, uploaded storage path when useful, and downstream details without signed URLs, bearer tokens, cookies, session values, app secrets, or refresh tokens.
  • Keep public content readers resilient: use current delivery payloads when available and app-local static fallback content when the Tuturuuu workspace is not configured or temporarily unavailable.

Read the full file on GitHub · 77 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. yesterday Changed · +12 lines · +8 tokens per session a1b9b90250c4
  2. 4d ago Changed · -29 tokens per session d009a72c0e8a
  3. 7d ago First seen · 65 lines · 55 tokens per session scan A 8e57ddffd901

Subscribe to this mod's changes

tuturuuu-external-apps is a skill published in the GitHub repository tutur3u/platform (53 stars, last pushed yesterday), licensed Apache-2.0. It adds 34 tokens to every session and 851 once invoked, about $0.0002 per session on Opus 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 2026-09-03.

Related

Other skills, from other repositories

frontend-engineer

!cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/input-validation.md 2>/dev/null || true !cat skills/shared/protocols/tool-efficiency.md 2>/dev/null || true !cat .production-grade.yaml 2>/dev/null || echo "No config — using defaults" !cat .forgewright/codebase-context.md…

buiphucminhtam/forgewright · 55 tokens

nextjs-app-router

Full end-to-end tRPC setup for Next.js App Router. Covers route handler with fetchRequestHandler (GET + POST exports), TRPCProvider with QueryClientProvider, createTRPCOptionsProxy for RSC prefetching, HydrateClient/HydrationBoundary for hydration, useSuspenseQuery for Suspense, and server-side callers.

trpc/trpc · 74 tokens

nextjs-pages-router

Set up tRPC in Next.js Pages Router with createNextApiHandler, createTRPCNext, withTRPC HOC, SSR via ssr option and ssrPrepass, SSG via createServerSideHelpers with getStaticProps, and server-side helpers for getServerSideProps prefetching.

trpc/trpc · 67 tokens

subscriptions

Set up real-time event streams with async generator subscriptions using .subscription(async function() { yield }). SSE via httpSubscriptionLink is recommended over WebSocket. Use tracked(id, data) from @trpc/server for reconnection recovery with lastEventId. WebSocket via wsLink and createWSClient from @trpc/client…

trpc/trpc · 118 tokens

client-setup

Create a vanilla tRPC client with createTRPCClient (), configure link chain with httpBatchLink/httpLink, dynamic headers for auth, transformer on links (not client constructor). Infer types with inferRouterInputs and inferRouterOutputs. AbortController signal support. TRPCClientError typing.

trpc/trpc · 63 tokens

links

Configure the tRPC client link chain: httpLink, httpBatchLink, httpBatchStreamLink, splitLink, loggerLink, wsLink, createWSClient, httpSubscriptionLink, unstablelocalLink, retryLink. Choose the right terminating link. Route subscriptions via splitLink. Build custom links for SOA routing. Link options: url, headers…

trpc/trpc · 90 tokens