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 JayRHa/AgentSkills --skill performance-profilergit clone --depth 1 https://github.com/JayRHa/AgentSkillsWrote 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/jayrha/agentskills/performance-profiler)<a href="https://agentmods.dev/skills/jayrha/agentskills/performance-profiler"><img src="https://agentmods.dev/badge/skills/jayrha/agentskills/performance-profiler/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/jayrha/agentskills/performance-profiler"><img src="https://agentmods.dev/badge/skills/jayrha/agentskills/performance-profiler.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 | $0.00154 | $0.01758 |
| Opus 5.5 | $0.00062 | $0.00703 |
| Sonnet 5.5 | $0.00031 | $0.00352 |
| Haiku 4.5 | $0.00015 | $0.00176 |
Grade A, and why
performance-profiler 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 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.
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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Profiler
Overview
Make slow things fast — correctly and provably. This skill enforces a measure-driven loop: never optimize on a hunch, always profile to find the real hot path, fix the biggest contributor first, then re-measure to confirm the win and guard against regressions.
Keywords: performance, profiling, optimization, bottleneck, latency, throughput, p99, slow, benchmark, flamegraph, CPU profile, memory leak, allocations, N+1 query, caching, big-O, complexity, hot path, regression.
The cardinal rule: measure first. Most "obvious" optimizations target the wrong code. Profilers routinely show that 90% of time sits in a place nobody suspected.
Workflow
Follow this loop. Do not skip steps — especially step 1 and step 6.
-
Define the goal and a metric. Pick ONE primary metric and a target: wall-clock latency (p50/p95/p99), throughput (req/s, rows/s), CPU time, peak memory (RSS), or allocations. Write down the current value and the target. "Make it faster" is not a goal; "cut p95 from 800ms to under 200ms" is.
-
Reproduce reliably. Build a repeatable scenario with representative data volume. A bottleneck at 10 rows may vanish at 10M and vice-versa. Disable noise: warm caches, JIT warmup, fixed input, quiet machine, multiple runs.
-
Measure the baseline. Time/benchmark the whole operation before touching anything. Save the numbers. Use
scripts/bench.pyfor a quick statistically sane wall-clock benchmark of a Python callable or shell command. -
Profile to find the hot path. Use a real profiler (not scattered print timers) to attribute cost. Find the function/line/query consuming the most time or memory. See
references/profiling-tools.mdfor the right tool per language and how to read its output. -
Diagnose and fix the top contributor. Apply the cheapest effective fix from the optimization hierarchy (see below). Change ONE thing at a time so each change's impact is attributable.
What ships with it
4 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.
- 1mo ago First seen · 142 lines · 154 tokens per session scan A 2c3b8276a7e1
performance-profiler is a skill published in the GitHub repository JayRHa/AgentSkills (12 stars, last pushed 2mo ago), licensed MIT. It adds 154 tokens to every session and 1,758 once invoked, about $0.0006 per session on Opus 5.5. 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
openclaw-debugger
Trigger when an OpenClaw agent is broken, silent, crashing, stuck, not responding, returning empty output, or the user says "my agent is down", "agent not working", "/openclaw-debugger". Walks through the standard OpenClaw 2026.4 diagnosis checklist and prints a report.
test-master
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.
debugging-wizard
Use when investigating errors, analyzing stack traces, or finding root causes of unexpected behavior. Invoke for error investigation, troubleshooting, log analysis, root cause analysis.
spec-miner
Use when understanding legacy or undocumented systems, creating documentation for existing code, or extracting specifications from implementations. Invoke for legacy analysis, code archaeology, undocumented features.
ast-grep
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for…
supreme-problem-solving
Genuine problem-solving discipline for Product Engineers, AI Engineers, ML Engineers, LLM Engineers, LLM Architects, and AI Researchers. Scales from simple bugs to complex system failures. Forces precise problem statements, reliable reproduction, 3–5 ranked falsifiable hypotheses, instrumented evidence…