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 skills add kok-o/contextos-agents --skill vercel-optimizegit clone --depth 1 https://github.com/kok-o/contextos-agentsWrote 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/skills/kok-o/contextos-agents/vercel-optimize)<a href="https://agentmods.dev/skills/kok-o/contextos-agents/vercel-optimize"><img src="https://agentmods.dev/badge/skills/kok-o/contextos-agents/vercel-optimize/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/skills/kok-o/contextos-agents/vercel-optimize"><img src="https://agentmods.dev/badge/skills/kok-o/contextos-agents/vercel-optimize.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 | $0.00116 | $0.00957 |
| Opus 5.5 | $0.00046 | $0.00383 |
| Sonnet 5.5 | $0.00023 | $0.00191 |
| Haiku 4.5 | $0.00012 | $0.00096 |
Grade A, and why
vercel-optimize 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 today.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vercel Optimize
Overview
Observability-first Vercel performance and cost reduction optimization skill. Evaluates deployed Next.js, SvelteKit, Nuxt, and Astro projects using production telemetry signals (signals.json), deterministic candidate gating, and code scanning to deliver ranked, verified architectural recommendations.
When to Use
- When tasked with reducing Vercel bills, Function Invocations, Fast Data Transfer, or Build Minutes.
- When diagnosing slow serverless routes, cold starts, or Edge vs Node runtime mismatches.
- When evaluating caching opportunities (
stale-while-revalidate, ISR, CDN edge caching) or Core Web Vitals degradation.
Rules & Patterns
1. Prerequisites & Framework Support
- Vercel CLI v53+ with
vercel metrics,vercel usage,vercel contract, andvercel api. - Authenticated CLI session (
vercel login) and linked app directory (vercel link). - Framework support: Next.js App Router (Full), Pages Router (Supported), SvelteKit (Supported), Nuxt (Supported), Astro (Limited).
- Security rule: Never put auth tokens in shell commands (
VERCEL_TOKEN=...is banned in chat/logs).
2. Core Doctrine & Gating Pipeline
- Metrics First: Recommendations start from Vercel production signals (14-day window), not repo-wide grep.
- Deterministic Gates:
scripts/gate-investigations.mjsselects code-scope and platform-scope candidates. - Candidate-Bound Scope: Inspect only files named by a candidate or a route-local import chain.
- Version-Aware Citations: Use only verified citations matching the target framework version.
- Specific Cache Policies: When recommending caching, state the exact cache policy and headers; keep auth-sensitive and error responses dynamic.
3. Recommendation Rules
- Every recommendation must trace to a launched candidate and include observed metric evidence.
- Cite verified files with line numbers when code changes are proposed.
- Use precise observed performance numbers; avoid customer-facing speculative
$Nsavings formulas. - Do not recommend duration reductions for Vercel Workflow runtime endpoints (
/.well-known/workflow/v1/*).
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today First seen · 84 lines · 116 tokens per session scan A b25941d505ca
vercel-optimize is a skill published in the GitHub repository kok-o/contextos-agents (10 stars, last pushed today), licensed Apache-2.0. It adds 116 tokens to every session and 957 once invoked, about $0.0005 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 2026-10-25.
Other skills, from other repositories
kubernetes-expert
Expert Kubernetes: workloads, services, config, probes, resources, and troubleshooting. Trigger keywords: Kubernetes, k8s, Deployment, StatefulSet, Service, Pod, ConfigMap, Secret, Ingress, liveness, readiness, probe, requests, limits, HPA, kubectl, Helm, CrashLoopBackOff, ImagePullBackOff, OOMKilled. Use for writing…
hosted-agents
Build background agents in sandboxed environments. Use for hosted coding agents, sandboxed VMs, Modal sandboxes, and remote coding environments.
env-setup
Configure l'environnement de développement pour un SaaS Next.js + Supabase + Vercel : outils CLI, variables d'env, RTK, vérifications.
deploy-check
Validation complète pré-déploiement. Supporte Vercel, Railway, Docker/VPS. Utilise les scripts Python du projet.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
huggingface-llm-trainer
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723…