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/kok-o/koko-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/rules/kok-o/koko-contextos-agents/performance)<a href="https://agentmods.dev/rules/kok-o/koko-contextos-agents/performance"><img src="https://agentmods.dev/badge/rules/kok-o/koko-contextos-agents/performance/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/rules/kok-o/koko-contextos-agents/performance"><img src="https://agentmods.dev/badge/rules/kok-o/koko-contextos-agents/performance.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 | $0.00005 | $0.00942 |
| Opus 5.5 | $0.00002 | $0.00377 |
| Sonnet 5.5 | $0.00001 | $0.00188 |
| Haiku 4.5 | $0.00001 | $0.00094 |
Grade A, and why
performance 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 1mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Web Performance
Web Performance & Core Web Vitals
Overview
Enforces high-efficiency frontend and full-stack performance standards to achieve exceptional Core Web Vitals: Largest Contentful Paint (LCP < 2.5s), Interaction to Next Paint (INP < 200ms), and Cumulative Layout Shift (CLS < 0.1).
When to Use
Activate whenever analyzing, profiling, writing, or optimizing page loading speeds, network waterfalls, script bundling, animation frame rates, or data caching.
Negative Constraints (What NOT to Do)
- NEVER introduce async waterfalls: Do not chain sequential
awaitcalls when requests can be executed concurrently viaPromise.all(). - NEVER import large full libraries when only a utility is needed: Never
import _ from 'lodash'; useimport debounce from 'lodash/debounce'or native alternatives. - NEVER render images or videos without explicit aspect ratios: Always provide
widthandheightoraspect-ratioto avoid Cumulative Layout Shift (CLS). - NEVER trigger synchronous layout thrashing: Do not alternate between reading layout properties (
offsetHeight,getBoundingClientRect) and writing styles in loops. - NEVER animate non-composited properties: Animate only GPU-composited CSS properties (
transform,opacity). Never animatewidth,height,top,left, ormargin.
Rules & Patterns
1. Vercel Optimization Hierarchy by Impact
| Priority | Category | Key Optimization Target | Expected Impact |
|---|---|---|---|
| 1. CRITICAL | Eliminating Waterfalls | Parallel data fetching (Promise.all), Suspense streaming |
30–60% faster LCP |
| 2. CRITICAL | Bundle Size Optimization | Direct submodule imports, next/dynamic, deferring 3rd party scripts |
40–70% smaller initial JS |
| 3. HIGH | Server-Side & RSC Caching | React.cache() request deduplication, edge SSR caching |
Lower TTFB & DB load |
| 4. MEDIUM-HIGH | Client Query Optimization | SWR / TanStack Query stale-while-revalidate, deduplication | Zero redundant network calls |
| 5. MEDIUM | Render & DOM Optimization | Virtualization for large lists, state colocation, :focus-visible |
Smooth 60 FPS / INP < 100ms |
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.
- 1mo ago First seen · 79 lines · 5 tokens per session scan A c3c139547bcd
performance is a cursor rule published in the GitHub repository kok-o/koko-contextos-agents (2 stars, last pushed 1mo ago), licensed MIT. It adds 5 tokens to every session and 942 once invoked, about $0.0000 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 2026-08-31.
Other cursor rules, from other repositories
deepen-architecture
Find deepening opportunities in a codebase, informed by the domain language in specs/tech-architecture/tech-stack.md and the decisions in specs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
craft-skill
Create new bigpowers skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill for the bigpowers lifecycle.
grill-me
Interactive assumption-surfacing Q&A that stress-tests a plan through relentless questioning until every decision is resolved. Use when user wants to challenge a plan, validate decisions from conversation/context, or mentions "grill me". For doc-grounded variant, use grill-with-docs.
run-planning
DISCOVER-PHASE ADVANCER — Drive the discover-phase checklist (specs/planning-status.yaml) through survey-context → scope-work → research-first → elaborate-spec → plan-release → slice-tasks. NOT a duplicate of plan-work or the planning spine; it orchestrates the pre-coding discover phase only.
slice-tasks
PLANNING SPINE STEP 2 of 3 — Slice the work: break a scoped PRD into vertical-slice stories in specs/epics/. Use after scope-work (step 1), before plan-work (step 3). Not a substitute for scope-work or plan-work.
terse-mode
Fallback ultra-compressed communication mode. Cuts token usage 75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use ONLY when context is critically long and compressing output is necessary to continue. Not a strategy — token discipline comes from code shape (small functions…