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 ao92265/claude-code-playbook --skill perf-checkgit clone --depth 1 https://github.com/ao92265/claude-code-playbookWrote 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/ao92265/claude-code-playbook/perf-check)<a href="https://agentmods.dev/skills/ao92265/claude-code-playbook/perf-check"><img src="https://agentmods.dev/badge/skills/ao92265/claude-code-playbook/perf-check.svg" alt="Measured on agentmods" 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 | $0.00082 | $0.00701 |
| Opus 5 | $0.00041 | $0.00351 |
| Sonnet 5 | $0.00016 | $0.00140 |
| Haiku 4.5 | $0.00008 | $0.00070 |
Grade A, and why
perf-check 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 7d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Investigation
Systematic approach to finding and fixing performance issues. Profile first, optimize second.
Steps
-
Define the problem:
- What's slow? (endpoint, page load, build, test suite, query)
- How slow is it? Get a baseline measurement
- What's the target? (e.g., "API response under 200ms")
- When did it start? (recent regression vs. always slow)
-
Profile before optimizing:
- Node.js:
--profflag,clinic.js, or0xfor flamegraphs - Frontend: Chrome DevTools Performance tab, Lighthouse
- Database:
EXPLAIN ANALYZEon slow queries - General: time the operation with
console.time()or equivalent - Record the baseline numbers precisely
- Node.js:
-
Identify the bottleneck:
- Where is time actually being spent? (CPU, I/O, network, database)
- Is it a single slow operation or death by a thousand cuts?
- Look for: N+1 queries, missing indexes, unnecessary re-renders, blocking I/O, large payloads
-
Prioritize fixes:
- Fix the biggest bottleneck first — often one fix solves 80% of the problem
- Estimate effort vs. impact for each potential fix
- Don't optimize things that aren't in the hot path
-
Implement the fix:
- Make ONE change at a time
- Common fixes: add database index, add caching, reduce payload, batch queries, lazy load, debounce
- Keep the code readable — clever optimizations that nobody can understand aren't worth it
-
Measure after:
- Run the same profile/benchmark as step 2
- Compare before/after numbers precisely
- Did it meet the target? If not, go back to step 3
-
Document the result:
- What was the bottleneck?
- What was the fix?
- Before/after numbers
- Any trade-offs made (memory vs. speed, complexity vs. performance)
Important
- Profile before optimizing. Guessing at bottlenecks wastes time on the wrong thing.
- Measure before AND after. "It feels faster" is not evidence. Numbers are evidence.
- One change at a time. Multiple simultaneous changes make it impossible to know what helped.
- Don't optimize prematurely. If it's fast enough, leave it alone.
- Readability > cleverness. A 10% speedup that makes code unreadable isn't worth it unless you're in a hot 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.
- 7d ago First seen · 69 lines · 82 tokens per session scan A 34b764063281
perf-check is a skill published in the GitHub repository ao92265/claude-code-playbook (10 stars, last pushed 21d ago), licensed MIT. It adds 82 tokens to every session and 701 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
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.