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 thienanblog/awesome-ai-agent-skills --skill performance-optimizationgit clone --depth 1 https://github.com/thienanblog/awesome-ai-agent-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/thienanblog/awesome-ai-agent-skills/performance-optimization)<a href="https://agentmods.dev/skills/thienanblog/awesome-ai-agent-skills/performance-optimization"><img src="https://agentmods.dev/badge/skills/thienanblog/awesome-ai-agent-skills/performance-optimization/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/thienanblog/awesome-ai-agent-skills/performance-optimization"><img src="https://agentmods.dev/badge/skills/thienanblog/awesome-ai-agent-skills/performance-optimization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00073 | $0.01030 |
| Opus 5 | $0.00036 | $0.00515 |
| Sonnet 5 | $0.00015 | $0.00206 |
| Haiku 4.5 | $0.00007 | $0.00103 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Optimization
Use this skill when performance is the main concern. Measure first, optimize the confirmed bottleneck, and verify improvement without changing business behavior accidentally.
Run this skill in the main conversation. Do not spawn subagents, agent teams, or delegated parallel workers unless the user explicitly approves the proposed count and scope after being told that doing so can increase usage. Ask again before expanding an approved scope.
Operating Rules
- Do not optimize blindly. Capture a baseline or concrete symptom first.
- Define a benchmark envelope before comparing results: workload, starting data, cache state, command and flags, resource limits, and concurrent activity.
- Read project docs, architecture notes, caching rules, database rules, design-system rules, and existing performance conventions.
- Preserve business logic and data correctness.
- Prefer low-risk local improvements before broad architecture changes.
- Treat caching as a contract: define invalidation, freshness, and user-specific data boundaries.
- Treat infrastructure health as part of correctness. Reject measurements with crashes, OOM kills, unexpected restarts, failed cleanup, or orphan processes.
- Avoid adding dependencies or infrastructure unless measurement justifies them.
- If the issue is actually a bug or regression with unclear cause, return
routing control to
project-development-mindsetand replace this workflow withdebugging-workflowwhen available. - Keep benchmarks, regression checks, and browser measurements inside this
workflow when they support performance work. Route to
testing-verificationonly if test or QA design becomes the primary deliverable.
Workflow
1. Define The Performance Claim
- Identify what is slow, where, for whom, and compared to what.
- Capture baseline evidence: timing, query count, payload size, memory, CPU, bundle size, Web Vitals, screenshot, profile, or logs.
- Identify the environment and data size used for measurement.
- Fix the workload and starting state. Record warm or cold cache, account and permissions, worker count, retries, resource limits, and unrelated workloads.
- For noisy measurements, run enough repetitions to report a representative value and spread instead of selecting the best run.
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.
- 10d ago First seen · 94 lines · 73 tokens per session scan A e000163c3b0c
performance-optimization is a skill published in the GitHub repository thienanblog/awesome-ai-agent-skills (65 stars, last pushed 12d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,030 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.