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/namingnpx skills add gridaco/grida --skill naminggit 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 | $0.00094 | $0.02350 |
| Opus 5 | $0.00047 | $0.01175 |
| Sonnet 5 | $0.00019 | $0.00470 |
| Haiku 4.5 | $0.00009 | $0.00235 |
Grade A, and why
naming 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- naming — 94% identical, 12 lines differ
How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Naming
Vanilla conventions (snake_case in Rust, kebab-case in JS/TS,
PascalCase exports, use-* hooks) are table stakes — assume them.
This document is about the observations on top: what a name commits
you to, what it reveals, and what it costs when it's wrong.
Name first
Pick the name before the types, before the tests, before the file exists. If the name doesn't come easily, the design isn't ready — don't start coding; sharpen the concept until the name falls out. Maintainability is downstream of naming. How a module grows, how cleanly it retires, how safely it can be deleted — all of it is decided at the moment you choose what to call it.
A strict, honest name is a scope gate
A name's primary job here is to refuse the wrong content. A
module called painter should feel actively wrong to host a
layout helper; a package called @grida/cmath should feel wrong
to host color logic. The strictness is deliberate — it is the
mechanism that keeps features from leaking into each other.
"Strict" requires "honest." A name that no longer describes what's inside has stopped being a gate: it won't reject foreign additions, and new readers can't trust it. When contents drift past the name, you have two moves — rename to match what the module has become, or extract the drifted pieces out — and you must pick one promptly. Letting a name go stale is how codebases rot quietly.
Three consequences cascade from the gate discipline, and together they produce the current repo structure:
- Modules stay shallow. You will rarely see a module nested
deeper than two levels inside a crate's
src/or a package'ssrc/. When you're tempted to grow a third level, the parent's name has stopped describing what's inside — flatten or extract, don't nest. - Flatten with prefixed siblings, or collapse into one file.
Before reaching for a subdirectory, ask whether the new thing is
a sibling variant of an existing file (
painter.rs+painter_debug_node.rs+painter_geometry.rs) or whether it collapses into the existing file. Both preserve the parent's scope; a new subdirectory quietly widens it. - If it resists flattening, it is a new module. The thing
that won't fit under the strict name doesn't belong there. It
wants its own tiny, agnostic package or crate. The repo has
many small
@grida/*packages and small crates precisely because this extraction was made each time a sibling would have diluted the parent's name.
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.
- 2d ago First seen · 218 lines · 94 tokens per session scan A 29305b6f93f4
naming is a skill published in the GitHub repository gridaco/grida (2,629 stars, last pushed 11d ago), licensed Apache-2.0. It adds 94 tokens to every session and 2,350 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…
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…
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…