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 ashtonian/llm-init --skill performance-auditgit clone --depth 1 https://github.com/ashtonian/llm-initWrote 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/ashtonian/llm-init/performance-audit)<a href="https://agentmods.dev/skills/ashtonian/llm-init/performance-audit"><img src="https://agentmods.dev/badge/skills/ashtonian/llm-init/performance-audit/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/ashtonian/llm-init/performance-audit"><img src="https://agentmods.dev/badge/skills/ashtonian/llm-init/performance-audit.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 | $0.00012 | $0.01530 |
| Opus 5.5 | $0.00005 | $0.00612 |
| Sonnet 5.5 | $0.00002 | $0.00306 |
| Haiku 4.5 | $0.00001 | $0.00153 |
Grade A, and why
performance-audit scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:8080/debug/pprof/goroutine?debug=2 How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Audit Skill
Structured workflow for conducting a systematic performance audit of the application. Identifies bottlenecks, measures baselines, and produces actionable recommendations.
Workflow
Step 1: Profile CPU and Memory
Run profiling tools to identify hot paths and allocation sites.
Go:
# CPU profile
go test -bench=. -cpuprofile=cpu.prof -benchtime=30s ./...
go tool pprof -http=:8080 cpu.prof
# Memory profile
go test -bench=. -memprofile=mem.prof -benchmem ./...
go tool pprof -http=:8080 mem.prof
# Goroutine profile (for concurrency issues)
curl http://localhost:8080/debug/pprof/goroutine?debug=2
Node.js:
# CPU profile
node --cpu-prof --cpu-prof-dir=./profiles app.js
# Then: chrome://inspect -> Open dedicated DevTools for Node
# Memory
node --heap-prof --heap-prof-dir=./profiles app.js
Frontend (Chrome DevTools):
- Performance tab: Record user interaction flow
- Memory tab: Heap snapshots before/after interaction
- Lighthouse: Overall performance score
Capture:
- Top 10 CPU-consuming functions
- Top 10 memory-allocating functions
- Goroutine/thread count under load
- GC pause times and frequency
Step 2: Identify Hot Paths and Allocation Sites
From profiling data, identify:
| Category | What to Find |
|---|---|
| CPU hot paths | Functions consuming >5% of total CPU |
| Memory allocations | Functions with >1000 allocs/op or >1MB/op |
| GC pressure | Allocation rate causing frequent GC pauses |
| Contention | Lock contention in concurrent code |
| I/O bottlenecks | Functions blocked on network/disk I/O |
For each finding, document:
- Function name and call chain
- Current metric (CPU%, allocs/op, bytes/op)
- Potential optimization approach
- Estimated improvement
Step 3: Benchmark Critical Endpoints
Use HTTP load testing tools to measure endpoint performance:
# Quick benchmark with hey
hey -n 10000 -c 50 -H "Authorization: Bearer $TOKEN" \
http://localhost:8080/api/v1/users
# Detailed benchmark with wrk
wrk -t4 -c100 -d30s -s scripts/post-user.lua \
http://localhost:8080/api/v1/users
# Multi-tenant load simulation with k6
k6 run --vus 100 --duration 60s scripts/multi-tenant-load.js
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.
- 1mo ago First seen · 220 lines · 12 tokens per session scan A af1393433a38
performance-audit is a skill published in the GitHub repository ashtonian/llm-init (2 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 1,530 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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.
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…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.