Agent Sh Perf
- 2 repo stars
- Updated July 22, 2026
- agent-sh/perf
agent-sh-perf is a Claude Code plugin that guides baselines, profiling, and evidence-backed performance decisions.
About
agent-sh-perf packages a performance investigation methodology for developers who ship web apps, APIs, and CLIs and cannot afford vague advice like optimize the database. The plugin emphasizes baselines first: capture numbers, form hypotheses, profile the hot paths, then change one variable at a time with evidence that justifies each decision. That rhythm fits teams without a dedicated performance engineer—especially when a feature branch suddenly doubles p95 latency or memory spikes under agent-driven load tests. It spans Ship when you are clearing launch checklists and Operate when production metrics drift, but the catalog shelf stays Ship/perf because that is where most developers first feel pain. Intermediate complexity: you should be comfortable reading profiler output or simple benchmarks. Pair it with your existing test harness; it is a workflow skill, not a hosted APM product.
- Rigorous performance investigation workflow with explicit baselines
- Profiling-guided steps instead of guess-and-check optimizations
- Hypothesis tracking with evidence-backed accept or reject decisions
- Suited to regressions caught in CI or staging before production ship
- agent-sh perf plugin bundle (single plugin entry in catalog)
Agent Sh Perf by the numbers
- Data as of Jul 23, 2026 (Skillselion catalog sync)
/plugin install agent-sh-perf@agent-sh/perfAdd your badge
Show developers this plugin is listed on Skillselion. Paste this into your README.
| repo stars | ★ 2 |
|---|---|
| Last updated | July 22, 2026 |
| Repository | agent-sh/perf ↗ |
What it does
Run a disciplined performance investigation with baselines, profiling, and hypothesis-driven fixes before you ship slow code.
Who is it for?
Best when you're shipping APIs or SaaS and hit slowdowns in staging or CI and need a structured perf ritual inside Claude Code.
Skip if: Skip if you want a hosted APM dashboard with auto-alerts and no hands-on profiling workflow.
What you get
You follow a repeatable investigation path from baseline to profile to validated fix, with documented evidence for each performance decision.
- Documented performance baselines and comparison after changes
- Profile-guided hypothesis log with accept/reject evidence
- Prioritized fix list tied to measured impact
By the numbers
- [object Object]
- [object Object]
Recommended Plugins
0xbigboss Linear CliLinear CLI built with Zig1
15195999826 LomomarketplaceLomo's Claude Code Plugin Marketplace1
1broseidon MarketplaceCurated collection of Claude Code plugins for fullstack development teams1
4rgon4ut Cc Zig LspZig LSP plugin for Claude Code4
708u TwigSimplify git worktree and branch management with configurable symlinks, change carrying, and cleanup.22
8avalon8 AvalonclaudemarketAvalon 的 Claude Code 插件市场How it compares
Evidence-backed perf investigation workflow, not a continuous monitoring SaaS or load-testing-only plugin.
FAQ
Who is Agent Sh Perf for?
Developers shipping backends or full-stack products who want agent-guided performance investigations with baselines and profiling, not random tuning tips.
When should I use Agent Sh Perf?
Use it when latency, throughput, or memory regressed and you need hypotheses tested against measurements before merging or releasing.
How do I add Agent Sh Perf to my agent?
Add the agent-sh/perf Claude Code plugin from Skillselion, ensure your project can run benchmarks or profilers locally, and start the perf workflow from the plugin commands.