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 lfyxhappy/lfcode --skill performance-profilergit clone --depth 1 https://github.com/lfyxhappy/lfcodeWrote 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/lfyxhappy/lfcode/performance-profiler)<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/performance-profiler"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/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/lfyxhappy/lfcode/performance-profiler"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/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 | $0.00053 | $0.00327 |
| Opus 5.5 | $0.00021 | $0.00131 |
| Sonnet 5.5 | $0.00011 | $0.00065 |
| Haiku 4.5 | $0.00005 | $0.00033 |
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.
What it actually says
Performance Profiler
Measure before optimizing and compare like with like.
Workflow
- Define the metric, workload, environment, and acceptable threshold. Record a baseline and warm-up conditions.
- Inspect the real entrypoint, hot path, I/O, concurrency, caching, allocations, and generated artifacts involved in the report.
- Use the profiler, tracing, timing, memory, browser, or package tools already available in the repository. Prefer repeatable samples over a single wall-clock observation.
- Separate product work from test or environment noise. Check whether logs, debug mode, cold caches, and fixture size explain the result.
- If optimization is requested, make the smallest change tied to a measured bottleneck and preserve correctness, cancellation, ordering, and resource cleanup.
- Re-run the same workload, compare baseline and result, and run focused regression tests plus typecheck or build as needed.
Boundaries
- Do not profile or alter production data, credentials, traffic, or process state without explicit authorization.
- Do not optimize speculative code or report a percentage without stating sample size and conditions.
- Treat memory or latency improvements as incomplete if correctness and error paths were not rechecked.
Completion check
Report the baseline, evidence, bottleneck, change if any, comparison result, and remaining measurement limitations.
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 · 28 lines · 53 tokens per session scan A 28bc04642ef4
performance-profiler is a skill published in the GitHub repository lfyxhappy/lfcode (2 stars, last pushed 26d ago), licensed MIT. It adds 53 tokens to every session and 327 once invoked, about $0.0002 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 2026-09-05.
Other skills, from other repositories
Debug (reproduce -> isolate -> fix)
Systematically diagnose and fix a bug instead of guessing.
feishu-troubleshoot
A Feishu troubleshooting tool with FAQs and diagnostic commands. Feishu is a collaboration platform with online documents and workplace services.
investigate
A structured root-cause investigation method for software bugs. It moves from history and reproduction through tested hypotheses, a focused fix, verification, and a report.
bugfix-triage
A method for locating the cause of a bug before changing code, using a minimal reproduction and step-by-step narrowing of the failing input and code path.
Review a GitHub PR (via gh)
Review a specific GitHub pull request with gh — fetch the diff, fan out reviewers, consolidate, and optionally post the review. Requires the gh CLI or the GitHub MCP server.
business-ops-runbook-generator
Build an operational runbook with rollback paths for a recurring task or incident: capture the brief, infer failure modes, draft the runbook steps and checks, then define a rollback path for each failure mode. Use when the user wants a step-by-step runbook that an operator can follow under pressure, including what to…