gg

A working guide for Grida Gateway, a company-hosted service that lets signed-in clients use text, image, and video AI without supplying their own model key. Usage is charged to the organization's prepaid credit.

In plain words
What is it for?
Use it when changing the scoped-token system, OpenAI-compatible text endpoints, image or video endpoints, billing boundaries, or desktop integration.
Why use it?
It gives developers a shared model for the gateway's authentication, AI endpoints, and usage metering. This keeps those parts aligned as the service is developed or separated from the main codebase.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/gridaco/grida/gg
Any agent
npx skills add gridaco/grida --skill gg
Clone the repo
git clone --depth 1 https://github.com/gridaco/grida

Made for: Claude Code, Codex.

Per session 165 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,652 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00165 $0.01652
Opus 5 $0.00082 $0.00826
Sonnet 5 $0.00033 $0.00330
Haiku 4.5 $0.00016 $0.00165

Measured 2d ago against content hash 2693eda18d13, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gg 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 2d 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.

.agents/skills/gg/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gg — Grida Gateway

Grida Gateway (GG) is Grida's first-party AI gateway: the path by which a signed-in client runs AI — text, image, video — without a user-supplied model key (no BYOK), billed to the organization's prepaid credit. It is one coherent, extractable surface, marked so a single grep finds all of it, and it is designed to spin out of this repo into a standalone service at grida.gg. Treat every touch as work on a product that will one day live on its own.

Canonical spec: Hosted AI (metered, no-BYOK). Security boundary: GRIDA-SEC-006 in SECURITY.md.

What counts as GG

The test: does this code exist to let a keyless client spend org credit on a Grida-hosted model? If yes, it is GG. Four surfaces:

  • token — the scoped-token mint + verify. A purpose-scoped, short-lived, org-bound JWT (audience gg:ai) is the only credential the gateway accepts. This surface is also GRIDA-SEC-006.
  • gateway — the server endpoints: the OpenAI-compatible text surface (chat completions, models) and the native image/video generation surfaces. They verify the gg:ai token and meter through the billing seam; they carry no billing logic of their own.
  • provider — the client-side gg provider kind (in the agent package) that resolves to the gateway, plus its in-memory session store, factories, and media adapters. It is the consumer of GG.
  • desktop — the renderer lifecycle that mints/re-mints the token and pushes it to the sidecar (memory-only custody), and the daemon gg capability/namespace that receives it.

Not GG: the billing ledger itself (that is ee-billing / grida_billing); the billing seam's providerOptions.grida namespace (Grida-billing's key, shared with GRIDA-SEC-003); BYOK providers (the carve-out GG sits beside).

The GRIDA-GG marker

Like GRIDA-EE, the surface is grep-able. Tag every file that exists only for GG, with the surface as the sub-label:

Read the full file on GitHub · 132 lines

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. 2d ago First seen · 132 lines · 165 tokens per session scan A 2693eda18d13

Subscribe to this mod's changes

gg is a skill published in the GitHub repository gridaco/grida (2,629 stars, last pushed 11d ago), licensed Apache-2.0. It adds 165 tokens to every session and 1,652 once invoked, about $0.0008 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 2026-08-30.

Related

Other skills, from other repositories

react-hook-form

Correct React Hook Form usage anywhere in the monorepo — data flow, subscriptions, reset, dirty state, number inputs, and controlled-input rules. Load this BEFORE writing or modifying ANY form code, adding a field to an existing form, touching watch/useWatch/formState/getValues/setValue/reset, wiring a form into a…

supabase/supabase · 123 tokens

safe-sql-execution

Use whenever code will build, return, fetch, or execute SQL that runs against a user's real Postgres database — even when the request reads like an ordinary feature or bug fix and never says "security," "injection," or "SafeSqlFragment." This covers: writing or editing any pg-meta function, query builder, or endpoint…

supabase/supabase · 221 tokens

clickhouse-logs-queries

Write, review, and migrate Supabase logs queries against the ClickHouse-backed logs table (the logs.all.otel analytics endpoint). Use this whenever a task involves Logs Explorer SQL, the logattributes map, querying a log source (edgelogs, postgreslogs, authlogs, etc.), translating an old BigQuery cross join…

supabase/supabase · 152 tokens

studio-e2e-tests

Write and run Playwright E2E tests for Supabase Studio (e2e/studio). Use when asked to run e2e tests, write new E2E tests, or debug flaky or failing Playwright tests. Covers running commands, avoiding race conditions, waiting strategies, selectors, helper functions, and CI vs local differences.

supabase/supabase · 74 tokens

studio-mock-api-tests

Component tests for Supabase Studio that mock API requests at the network layer with MSW. Use when writing or reviewing a component test that exercises a React Query hook or mutation, or when migrating an existing test away from vi.mock('@/data/...'). Covers the customRender + addAPIMock template and the jsdom/MSW…

supabase/supabase · 79 tokens

ask-the-docs

Answer questions about the Supabase docs app (apps/docs) using documented architecture, build pipeline, and review-pattern notes, and apply feature-design principles (codebase reuse, coding minimalism) when proposing or critiquing changes. Use when the user asks "how does X work in the docs app?", "where does Y…

supabase/supabase · 129 tokens