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/whitequeen306/code-cortex-loop/performance-optimizationnpx skills add whitequeen306/code-cortex-loop --skill performance-optimizationgit clone --depth 1 https://github.com/whitequeen306/code-cortex-loopWhat 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 | $0.00036 | $0.01441 |
| Opus 5 | $0.00018 | $0.00720 |
| Sonnet 5 | $0.00007 | $0.00288 |
| Haiku 4.5 | $0.00004 | $0.00144 |
Grade A, and why
performance-optimization 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Optimization
Methodology adapted from performance-deity (MIT). Every optimization must be proven with real numbers.
Overview
Optimize code by measuring first, analyzing bottlenecks, applying targeted fixes, and proving improvement with before/after benchmarks. Never guess at performance — measure, fix, verify.
When to Use
- Code review flags slow paths, N+1 queries, or unbounded operations
/cortexloopperformance pass- User reports latency, jank, or high memory usage
- Before/after a refactor that touches hot paths
- React/Next.js apps with unnecessary re-renders
- API endpoints with missing pagination or eager loading
When NOT to use:
- Code is not on a hot path and no measurable problem exists
- Premature optimization would harm readability without measurable gain
- You cannot run benchmarks in the current environment (note this and use static analysis only)
The Four Phases (Required)
Execute all four phases in order. Do not skip any phase when applying fixes in Direct mode.
Phase 1 — Establish Baseline
- Identify the exact code path to optimize (function, query, component, endpoint).
- Run a micro-benchmark:
- Write a temporary benchmark script in the workspace.
- Include a warm-up phase (≥10 iterations, discard results).
- Run ≥100 iterations; record Average and P95 execution time.
- Run via terminal, then delete the temporary script.
- Fallback: use
time/ built-in profilers if the script fails due to missing deps.
- Record baseline numbers before writing any optimized code.
- In Report mode, include baseline numbers in the finding even if no fix is applied yet.
Phase 2 — Algorithmic Analysis
State explicitly:
- Time complexity (Big-O) of the current implementation
- Space complexity and primary allocation sites
- Bottleneck in one precise sentence, e.g.:
- "Nested loops causing O(n²) scaling"
- "N+1 query: one SELECT per item in loop"
- "Full table scan — missing index on
user_id" - "React parent re-render cascades to all list items"
- "Synchronous file read blocks event loop"
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 · 159 lines · 36 tokens per session scan A 3286cb8c2565
performance-optimization is a skill published in the GitHub repository whitequeen306/code-cortex-loop (15 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 1,441 once invoked, about $0.0002 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…