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 tushaarmehtaa/tushar-skills --skill performance-diagnosisgit clone --depth 1 https://github.com/tushaarmehtaa/tushar-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/tushaarmehtaa/tushar-skills/performance-diagnosis)<a href="https://agentmods.dev/skills/tushaarmehtaa/tushar-skills/performance-diagnosis"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/performance-diagnosis/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/tushaarmehtaa/tushar-skills/performance-diagnosis"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/performance-diagnosis.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 | $0.00048 | $0.00634 |
| Opus 5 | $0.00024 | $0.00317 |
| Sonnet 5 | $0.00010 | $0.00127 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
performance-diagnosis 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 11d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance diagnosis
Measure a reproducible slow path before changing it. Diagnosis does not authorize a fix unless the user requested implementation.
Workflow
- Establish the symptom, affected environment, route/action, regression window, expected threshold, and a repeatable reproduction. Infer these from traces/issues/code when possible; ask only for missing facts that change the investigation.
- Detect framework/runtime/version, deploy topology, package manager, data stores, observability, and recent relevant diffs. Separate development-only behavior from production behavior.
- Attribute resource symptoms before profiling the application. For heat, fan, battery, or system-wide spikes, use a short, thermally safe reproduction and sample process CPU, memory, energy, and GPU where available. Isolate the browser tab from extensions, the Node/dev server, compiler watchers, database, and unrelated processes. Stop the reproduction if temperature, power draw, or system stability becomes unsafe.
- Capture a baseline with the tool suited to the symptom:
- dev/build: timed cold and warm start/build, compiler logs, watcher scope;
- server: route spans, CPU/memory profile, cold start, event-loop delay, query timing;
- browser: tab/task-manager isolation, performance trace, network waterfall, long tasks, hydration, animation/compositor/GPU load, polling/timers, and Core Web Vitals;
- bundle: framework-supported analyzer and route-level client/server composition;
- database/network: query plans, connection waits, downstream latency and payload size.
- Form ranked hypotheses and test the cheapest discriminating one first. A large log, expensive-looking call, or large package is evidence to investigate, not proof of root cause.
- For Next.js, detect the major version and caching model before recommending
React.cache,use cache, fetch caching, or Turbopack settings.React.cachededuplicates within a request; it is not a cross-request cache. Configureturbopack.rootonly when the project truly resolves linked files outside the detected root. - If implementation is authorized, make one narrow change at a time. Protect user/tenant isolation, freshness, invalidation, memory bounds, and failure behavior when caching. Preserve a before/after artifact and revert changes that do not improve the target metric.
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.
- 11d ago First seen · 33 lines · 48 tokens per session scan A aa59875f97c6
performance-diagnosis is a skill published in the GitHub repository tushaarmehtaa/tushar-skills (11 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 634 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
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.