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/gotgenes/pi-anthropic-auth/code-designnpx skills add gotgenes/pi-anthropic-auth --skill code-designgit clone --depth 1 https://github.com/gotgenes/pi-anthropic-authWhat 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 | $0.00072 | $0.03590 |
| Opus 5 | $0.00036 | $0.01795 |
| Sonnet 5 | $0.00014 | $0.00718 |
| Haiku 4.5 | $0.00007 | $0.00359 |
Grade A, and why
code-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 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Design
Load this skill when implementing, refactoring, or reviewing TypeScript code.
Self-Documenting Code
Code should be its own primary documentation. Prefer names that reveal intent — for functions, methods, classes, variables, and modules.
Names over comments
If a comment is needed to explain what code does, extract a well-named function or rename the symbol. Comments should explain why — the reasoning or non-obvious context behind a decision. Do not leave tombstone comments that narrate removed code or the absence of a guard, test, or branch — the type system and the diff already document it.
Scope-appropriate naming
Name length should correspond to scope.
Short names (i, x, fn) are fine for small scopes (loop counters, short lambdas).
Exported functions, module-level variables, and class names warrant longer, descriptive names.
Doc comments
Add JSDoc/docstrings where the ecosystem expects them — typically on public/exported APIs. Do not add doc comments when the name and signature already convey usage.
Code Organization
Source files should read like a newspaper article: high-level intent at the top, progressively deeper detail as you read down.
Public API first
Exported functions, classes, and interfaces appear near the top so readers can scan the module's surface without wading through implementation details.
Stepdown rule
Each function should be followed by the helpers it calls, at the next level of abstraction — caller first, then the helpers it depends on. Related functions that collaborate on the same data should be grouped together. When extracting a helper during a refactor, place it below the function that calls it, not above — function declarations hoist, so "define before use" is unnecessary and inverts the stepdown order.
Helpers stay in the file
Private helper functions remain in the same file as the code that uses them. When private helpers accumulate to the point where they warrant their own tests, extract them into a new module with its own public API.
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 · 252 lines · 72 tokens per session scan A cf330850d6b5
code-design is a skill published in the GitHub repository gotgenes/pi-anthropic-auth (227 stars, last pushed 16d ago), licensed MIT. It adds 72 tokens to every session and 3,590 once invoked, about $0.0004 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
zapier-sdk
Zapier SDK for TypeScript. Programmatic access to 9,000+ apps on a user's behalf via Zapier's OAuth and audit layer. Use when writing code that needs to run actions in third-party apps (send an email, upsert a CRM record, look up a spreadsheet row, post to a chat) without managing per-app OAuth or vendor SDKs.…
fastify
Fastify usage for QAuth — plugin authoring (encapsulation, decorators, lifecycle), route schemas with the Zod type provider, production/reverse-proxy setup, and the Fastify version/CVE requirement. Use when adding or modifying @qauth-labs/fastify-plugin- libraries, auth-server routes, or deployment config.
effect-http-api
Build typed HTTP APIs with Effect's HttpApi — endpoints with schemas, handlers, security middleware, OpenAPI docs, derived clients, and handler unit tests. Use when building HTTP servers, REST APIs, or typed HTTP clients with Effect v4.
effect-error-handling
Implement typed error handling in Effect v4 using Schema.TaggedErrorClass, catchTag/catchTags, catchReason/catchReasons, Cause, ErrorReporter, and recovery patterns. Use this skill when working with Effect error channels, handling expected failures, or designing error recovery strategies.
effect-http-server
Build HTTP servers with effect/unstable/http — HttpRouter routes and middleware, HttpServerRequest schema decoding, HttpServerResponse constructors, multipart uploads, websocket upgrades, static files, NodeHttpServer/BunHttpServer layers, and in-memory web handlers. Use when serving raw HTTP routes, reading request…
effect-fiber
Fork, supervise, and interrupt Effect fibers with Effect.forkChild/forkScoped/forkIn/forkDetach, Fiber join/await/interrupt, uninterruptible regions, and the FiberHandle/FiberMap/FiberSet supervision collections. Use when running background work, cancelling or restarting tasks, implementing latest-wins or keyed…