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/vvedantb/eva/quality-codenpx skills add vvedantb/eva --skill quality-codegit clone --depth 1 https://github.com/vvedantb/evaWhat 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 | $0.00055 | $0.00752 |
| Opus 5 | $0.00028 | $0.00376 |
| Sonnet 5 | $0.00011 | $0.00150 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
quality-code scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing quality full-stack TypeScript
Apply these principles when writing or reviewing TypeScript code.
Make impossible states unrepresentable
Use the type system to make invalid states fail at compile time. Fewer reachable states = easier code to read and change.
Branded types
Brand primitives so they can't be mixed up. Validate once at the boundary; downstream code trusts the type.
type PhoneNumber = string & { __brand: "PhoneNumber" };
function parsePhone(input: string): PhoneNumber {
if (!/^\+?\d{10,15}$/.test(input)) throw new Error(`Invalid: ${input}`);
return input as PhoneNumber;
}
function sendSMS(to: PhoneNumber, body: string) {
/* input is trusted */
}
If the project already uses a library with native branded-type support (e.g. Effect), use their primitives instead of rolling your own.
Discriminated unions over flag bags
// Don't — invalid combos representable
type State = { loading: boolean; user?: User; error?: string };
// Do — only valid states exist
type State =
| { status: "loading" }
| { status: "success"; user: User }
| { status: "error"; error: string };
Let the types flow end-to-end
DB schema → server → client should share types without manual duplication. Use whatever end-to-end type tool the project already has (tRPC, oRPC, Elysia, TanStack Start). A users.email branded as Email should arrive on the client still branded.
Don't restate types you can derive. Reach for Pick, Omit, Parameters, ReturnType, Awaited, typeof etc. before writing a new interface. For function arguments, infer from the source instead of typing them by hand:
// Don't — duplicate shape, drifts when the row changes
type UserSummary = { id: string; email: Email };
function renderUser(u: UserSummary) {
/* ... */
}
// Do — derive from the source of truth
type User = Awaited<ReturnType<typeof db.query.users.findFirst>>;
function renderUser(u: Pick<User, "id" | "email">) {
/* ... */
}
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 · 94 lines · 55 tokens per session scan A b5294e271ff2
quality-code is a skill published in the GitHub repository vvedantb/eva (101 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 752 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…