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 ashermahonin/agentic-skills --skill perf-and-memorygit clone --depth 1 https://github.com/ashermahonin/agentic-skillsWrote 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/ashermahonin/agentic-skills/perf-and-memory)<a href="https://agentmods.dev/skills/ashermahonin/agentic-skills/perf-and-memory"><img src="https://agentmods.dev/badge/skills/ashermahonin/agentic-skills/perf-and-memory/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/ashermahonin/agentic-skills/perf-and-memory"><img src="https://agentmods.dev/badge/skills/ashermahonin/agentic-skills/perf-and-memory.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 | $0.00084 | $0.00456 |
| Opus 5 | $0.00042 | $0.00228 |
| Sonnet 5 | $0.00017 | $0.00091 |
| Haiku 4.5 | $0.00008 | $0.00046 |
Grade A, and why
perf-and-memory 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 9d 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
Performance and Memory
Purpose
Keep performance work honest. Find the bottleneck with evidence, choose the simplest useful intervention, and make sure the result can be measured again.
Change context
- Identify the user-visible or system-visible performance problem.
- Choose the metric: latency, throughput, memory, CPU, allocations, query count, startup, bundle size, or cost.
- Find existing benchmarks, traces, logs, or production signals.
- Name the language/runtime constraints that matter.
Change method
- Form a hypothesis and measurement plan before optimizing.
- Collect baseline evidence or state why baseline cannot be collected.
- Look for algorithmic issues, I/O bottlenecks, query shape, caching boundaries, concurrency limits, allocation churn, and serialization overhead.
- Recommend or implement the smallest change likely to move the metric.
- Re-measure after the change when possible.
- Record tradeoffs: complexity, correctness risk, cache invalidation, resource cost, and rollback.
Engineering constraints
- Use Context7 MCP for current library, framework, platform, API, CLI, and configuration documentation whenever the task depends on external technology behavior.
Evidence
- Performance hypothesis
- Baseline and target metric
- Profiling or benchmark plan
- Optimization recommendation
- Validation evidence
- Language profile update
Ready when
- Never optimize an unnamed metric.
- Do not claim improvement without measurement or a clear reason measurement was impossible.
- Treat caching as a correctness and invalidation problem, not a magic speed button.
- Prefer reducing work over hiding work.
Handoff
Hand off metric, evidence, changed constraints, and regression checks to implementation, QA, or review.
References
references/language-profile-template.md: Use this for language-specific performance notes.
What ships with it
2 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.
- 9d ago First seen · 55 lines · 84 tokens per session scan A 1600011db444
perf-and-memory is a skill published in the GitHub repository ashermahonin/agentic-skills (10 stars, last pushed 15d ago), licensed MIT. It adds 84 tokens to every session and 456 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…