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/nothing/sdk-designnpx skills add gridaco/nothing --skill sdk-designgit clone --depth 1 https://github.com/gridaco/nothingWhat 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 | $0.00192 | $0.03459 |
| Opus 5 | $0.00096 | $0.01729 |
| Sonnet 5 | $0.00038 | $0.00692 |
| Haiku 4.5 | $0.00019 | $0.00346 |
Grade A, and why
sdk-design 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.
This is a copy
95% identical to sdk-design — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sdk-design
This is not a style guide. Style and language-specific code shape are downstream (see $code-ts, $code-react for the TS sides). This is about what an SDK refuses to do — the discipline that keeps a package small, legible, and replaceable, regardless of language.
The thesis
An SDK lives or dies by what it refuses to expose. Default is core; customization is the exception. Every public knob is a contract you cannot retract without a semver break and a coordinated migration across every downstream call site.
A library with too few knobs is easy to grow. A library with too many is impossible to retire. The asymmetry is brutal — design from it.
This doctrine applies whether the package ships as an npm scope, a crate, a header-only library, a WASM module, a Python wheel, a hosted service with an SDK, or a pair of microservices defining a shared message vocabulary. The mechanics of "publish" differ; the discipline of "refuse the wrong contents" does not.
Scope: what counts as an SDK
This is the gate. The skill says "SDK," not "package," because the two are different. An SDK is:
- A surface that crosses a foreign-or-foreign-treated boundary. Published to a registry (
npm,crates.io,PyPI); linked by a separately-versioned consumer (a desktop binary against a crate, a generated WASM/FFI binding); or authored as if a foreign consumer existed even if one doesn't yet (any package whose README documents it as a public surface, anything tagged for publication, anything in a*-hostedsuffix family). - Versioned independently of its callers, even if today every caller lives in the same monorepo and ships on the same commit. The intent to be replaceable is what counts.
What this excludes — where the doctrine is welcome but not load-bearing:
- A package with exactly one internal caller, shipping on the same commit, where if the caller's needs changed the package would be rewritten freely. That's not an SDK; that's a refactored module that happens to live in
packages/. Adopt the parts of this skill that pay; skip the rest without apology. - One-off helper crates pulled in by a single binary in
crates/. Same logic.
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 · 285 lines · 192 tokens per session scan A e3c71a64acb8
sdk-design is a skill published in the GitHub repository gridaco/nothing (43 stars, last pushed 2d ago), licensed Apache-2.0. It adds 192 tokens to every session and 3,459 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to sdk-design, differing in 7 lines, and is treated as a copy.
Other skills, from other repositories
freya
Freya Rust GUI framework best practices, patterns, and conventions. Use when writing Freya components, hooks, elements, or working on a Freya project.
docs-svg-kit
Author SVG figures for Grida docs — diff-able, version-controlled vector diagrams embedded in doc pages instead of screenshots. Provides reusable primitives (selection chrome, size badges, anchor pins, resize cursors, click ripples), color/typography tokens, a starter template, and finished examples to crib from.…
editor-perf
Guides performance investigation, benchmarking, and optimization of the Grida Canvas web editor (TypeScript reducer, Immer, React hooks). Use when profiling reducer dispatch cost, diagnosing slow interactions (drag, resize, color change), writing or running editor benchmarks, instrumenting with PerfObserver, or…
sdk-seam
Discipline for the seam between two SDKs (or two sides of one contract) that the same hand writes. The failure mode: "we own both sides" produces dirty contracts no foreign reviewer would accept. The exercise: pretend the other side is FFI, IPC, or a network protocol you cannot rewrite. Spawn an adversarial subagent…
agent-system
Grida AI agent system work: @grida/daemon (DaemonServer, loopback HTTP perimeter, files/workspaces, secrets store, daemon discovery) and @grida/agent (the agent tenant: sessions, providers/BYOK, runtime/tool execution, skills discovery, prompts, tiers, sandbox hosts). Use for packages/grida-daemon/…
ai-models
Research, compare, and update AI model configurations. Covers text model tiers, image and video generation models, image tool models, pricing data sourcing, and provider-cost metering against prepaid org credit. Use when bumping model versions, adding new models, updating pricing, or auditing model specs against…