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/eenpx skills add gridaco/grida --skill eegit 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 | $0.00103 | $0.01391 |
| Opus 5 | $0.00051 | $0.00696 |
| Sonnet 5 | $0.00021 | $0.00278 |
| Haiku 4.5 | $0.00010 | $0.00139 |
Grade A, and why
ee 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ee
Grida is open source. Some features only exist because Grida is also a hosted commercial product — org-level entitlement, custom domains, billing. Those features are EE (enterprise edition): they ship in the same monorepo as the OSS core, but a self-hoster running the codebase without paid infrastructure should be able to identify and strip them.
This skill is the anchor for that boundary. No GRIDA-EE marker
exists in the repo today; this skill establishes the convention.
What counts as EE
The test: would this feature still make sense in a single-user, no-billing self-hosted instance? If no, it is EE.
Three surfaces today:
- Org / entitlement — the commercial layer on top of multi-tenant
routing. Paid plans, member seats, the entitlement check that gates
paid features. The tenant routing substrate itself (
(tenant)route group, RLS, hostname resolution) is OSS infrastructure — only the commercial layer on top of it is EE. - Custom domains (BYOD) — user-owned apex + subdomain mapping on Vercel. See multi-tenant-custom-domain-vercel.
- Billing — subscriptions, AI credit, the entitlement gate
primitive. See the
ee-billingskill (planned) for the workflow.
The GRIDA-EE marker
Like GRIDA-SEC, the boundary is grep-able. Tag every file that
exists only for EE, with the surface as the sub-label:
// GRIDA-EE: entitlement — paid-plan gate
// GRIDA-EE: byod — apex domain verification
// GRIDA-EE: billing — see ee-billing
Sub-labels are surface names (entitlement / byod / billing),
not ids — there is no central registry like SECURITY.md. The grep
is the index:
grep -rn 'GRIDA-EE' editor crates packages
Tag the file header when the entire file is EE; tag inline when only a branch is EE.
Known limitation. The marker captures files that exist only for EE. Shared utilities that EE imports but OSS also uses are not tagged — strip-time discovery has to come from an import audit, not grep. Don't tag OSS modules with EE callers; tag inline at the EE branch instead.
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.
- yesterday First seen · 129 lines · 103 tokens per session scan A d1ac4a8df6e7
ee is a skill published in the GitHub repository gridaco/grida (2,624 stars, last pushed 11d ago), licensed Apache-2.0. It adds 103 tokens to every session and 1,391 once invoked, about $0.0005 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…