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.
git clone --depth 1 https://github.com/textura-agency/next16-claude-starterWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/textura-agency/next16-claude-starter/perf)<a href="https://agentmods.dev/commands/textura-agency/next16-claude-starter/perf"><img src="https://agentmods.dev/badge/commands/textura-agency/next16-claude-starter/perf/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/textura-agency/next16-claude-starter/perf"><img src="https://agentmods.dev/badge/commands/textura-agency/next16-claude-starter/perf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00019 | $0.00625 |
| Opus 5.5 | $0.00008 | $0.00250 |
| Sonnet 5.5 | $0.00004 | $0.00125 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
perf 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 10d 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.
What it actually says
Optimise scroll performance for: $ARGUMENTS (the home route if empty).
Use the optimize-performance skill. If the project renders a three.js / WebGL
scene, run optimize-3d-scene first. The loop is the point — build, measure,
attribute, fix one thing, re-measure:
yarn build && yarn start— never measurenext dev.yarn qa:setuponce.- Baseline first:
node tools/qa/scroll-test.mjs --url http://localhost:3000/— PC (wheel) and mobile (touch, 4× CPU, 4G), cold then warm, 3 runs; every frame over 50 ms with its section, cause and reproducibility. Add--first-scrollwhen the page has a loader. On a WebGL page alsonode tools/qa/fps-probe.mjs --url …(the scene's real draw rate). - Attribute before fixing. Cold bad / warm clean = first-visit work inside
animating frames. A
gpu / rasterframe with the main thread idle is GPU work (blur per letter, layer promotion, fill) — not JavaScript. Name the code withnode tools/qa/profile.mjs --url … --scroll-to "<selector>". - Fix one thing, re-measure with the identical config (interleave A/B runs
on a busy machine). Check the fix-catalog first:
obsidian/knowledge/fix-catalog.md. .claude/scripts/verify.sh,yarn lint,yarn build,node tools/qa/check-motion.mjs --url …, andqa-verifyif any UI changed — a perf fix that silences a reveal is not a win. Anything a phone shows changed →mobile-device-qa.- Retro — a measured fix worth reusing →
obsidian/knowledge/fix-catalog.md(symptom, fix, before → after, rule/observed); a reading that misled you →obsidian/knowledge/pitfalls.md; a skill that was wrong → edit it.
The bar: ideal on PC and mobile — no frame over 50 ms, ≤ 1 % dropped, p99 ≤ 33 ms, cold and warm. Never add a fixed phone frame cap to get there.
Report the before and after verdicts with the config (and machine load) they were taken under, what you changed, what you reverted, and what you did not fix and why. Never report a win you did not re-measure; never trade visual weight without screenshots and the client's sign-off.
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.
- 10d ago Changed · +13 lines · +4 tokens per session 76ae45bacbf6
- 29d ago First seen · 26 lines · 15 tokens per session scan A 55d0b8160435
perf is a command published in the GitHub repository textura-agency/next16-claude-starter (137 stars, last pushed 3d ago), licensed Unlicense. It adds 19 tokens to every session and 625 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-18.
Other commands, from other repositories
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
react-native
Command "react-native" from getsentry/toolkit, covering examples, also associate with a release and distribution(s), xcode build step (react-native xcode) and important notes.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
doctor
Badi configuration validation. Checks all Badi components and produces a diagnostic report.
http-service
Build, review or debug a Bun HTTP service. Loads the http-service skill, then works the task through its workflow.
auditar-cascading
Invoca cascading-failures-auditor — audita serviço para 5 triggers de cascade (sem timeout, retry sem jitter, sem circuit breaker, sem deadline, queue unbounded) e gera CASCADING-AUDIT.md.