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 agentmods add skills/gridaco/grida/ai-modelsnpx skills add gridaco/grida --skill ai-modelsgit clone --depth 1 https://github.com/gridaco/gridaWhat 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 | $0.00065 | $0.03387 |
| Opus 5 | $0.00032 | $0.01693 |
| Sonnet 5 | $0.00013 | $0.00677 |
| Haiku 4.5 | $0.00006 | $0.00339 |
Grade A, and why
ai-models 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 3d 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Models — Research & Update Workflow
When to Use This Skill
- Bumping a text, image, or video model to a newer version
- Adding a new image/video generation model or provider (Vercel gateway, Replicate, fal.ai)
- Updating pricing data (per-token, per-image flat, per-image tiered, per-second)
- Verifying model specs (context window, output limit, cost) against providers
- Auditing hosted usage metering against prepaid organization credit
Key Files
| File | Role |
|---|---|
packages/grida-ai-models/src/models.ts |
Central catalogue. Sole export is the models namespace: models.text (ModelSpec, catalog, byTier, modelSpecById), models.image, models.audio, models.video, models.image_tools |
packages/grida-ai-models/src/tiers.ts |
ModelTier set + TIER_MODEL_IDS (type-uses models.text.CatalogId from models.ts) |
editor/lib/ai/models.ts |
AI Gateway + BYOK provider seam (catalogue is re-exported from @grida/ai-models) |
editor/lib/ai/ai.ts |
toMills() + Replicate call shapes; re-aggregates the shared catalogue under ai.* |
editor/lib/ai/server.ts |
AI seam: prepaid-credit gate, provider call, and post-flight usage ingest |
editor/lib/billing/metronome.ts |
Organization credit entitlement, cached balance gate, and Metronome usage ledger |
editor/app/(www)/(ai)/ai/models/page.tsx |
Public models catalog page |
docs/models/index.md |
User-facing models & pricing documentation |
What ships with it
1 file 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.
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.
- 3d ago First seen · 229 lines · 65 tokens per session scan A 2a56ee6d7506
ai-models is a skill published in the GitHub repository gridaco/grida (2,629 stars, last pushed 12d ago), licensed Apache-2.0. It adds 65 tokens to every session and 3,387 once invoked, about $0.0003 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.
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…
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…
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.
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…
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…
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…