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/emilyli2020/wave/quickstartnpx skills add emilyLi2020/WAVE --skill quickstartgit clone --depth 1 https://github.com/emilyLi2020/WAVEWhat 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 | $0.00079 | $0.01514 |
| Opus 5 | $0.00039 | $0.00757 |
| Sonnet 5 | $0.00016 | $0.00303 |
| Haiku 4.5 | $0.00008 | $0.00151 |
Grade A, and why
quickstart 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quickstart
The user is staring at an empty repo and wants to go from zero to a running full-stack scaffold in one command. This skill chains the three foundational skills in the right order so the user does not have to remember them.
The pipeline is:
domain-to-spec → scaffold-frontend → scaffold-backend (optional)
(writes PRD) (reads PRD, builds (reads PRD, builds
clients/) server/ if needed)
Preflight
Before starting, check the repo state:
test -f AGENTS.md && echo "AGENTS_EXISTS"
test -f PRD.md && echo "PRD_EXISTS"
test -d clients && echo "CLIENTS_EXISTS"
test -d server && echo "SERVER_EXISTS"
If any of AGENTS.md, PRD.md, clients/, or server/ already exist, STOP and show the user what was found. Ask:
"I found existing files from a previous run. Do you want to (a) skip steps whose output already exists, (b) overwrite everything and start fresh, or (c) cancel?"
Respect the answer. Never overwrite silently.
Step 1: Run domain-to-spec
Invoke the domain-to-spec skill end-to-end. Do not summarize it. Do not skip any of its questions. The user must complete the full Q&A so the PRD is properly filled in.
When domain-to-spec finishes, both AGENTS.md and PRD.md should exist at the repo root. Verify:
test -f AGENTS.md && test -f PRD.md && echo "STEP_1_OK" || echo "STEP_1_FAILED"
If the check fails, STOP. Do not proceed to Step 2. Ask the user to retry domain-to-spec or investigate why the files were not created.
Step 2: Pause for User Review
Before running any scaffolds, show the user:
- The
## Pages / Screenstable fromPRD.md. - The
## Backend Needed?line fromPRD.md. - The
## Backend Routessection fromPRD.md(if backend is needed).
Ask:
"Review these sections. Are the pages, backend decision, and routes correct? Reply 'yes' to continue, or paste corrections and I will update
PRD.mdbefore scaffolding."
If the user pastes corrections, update PRD.md in place, then re-show the sections and ask again. Only proceed when the user confirms.
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 · 144 lines · 79 tokens per session scan A 31babccc4888
quickstart is a skill published in the GitHub repository emilyLi2020/WAVE (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,514 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 2026-08-31.
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…