perf

perf is a command for Claude Code from smrafiz/claude-supercharger. It costs 0 tokens per session (382 once invoked), scanned A, original, MIT.

A command that displays timing data for development hooks, which are automated checks run during coding tasks.

In plain words
What is it for?
Use it to view slow hooks or timing data for a chosen number of days, identify hooks over 200 milliseconds, and inspect total overhead when timing data exists.
Why use it?
It helps identify slow checks and measure how much time hooks add to each Claude invocation.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the supercharger plugin — 37 commands, 10 agents, 28 hooks shipped together

Good fit Use it to view slow hooks or timing data for a chosen number of days, identify hooks over 200 milliseconds, and inspect total overhead when timing data exists.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add smrafiz/claude-supercharger
Claude Code
/plugin install supercharger

Made for: Claude Code.

Or install supercharger, the plugin that ships this one along with the rest of its 37 commands, 10 agents, 28 hooks.

Wrote 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.

agentmods badge for perf

README.md
[![agentmods](https://agentmods.dev/badge/commands/smrafiz/claude-supercharger/perf.svg)](https://agentmods.dev/commands/smrafiz/claude-supercharger/perf)
Your own site
<a href="https://agentmods.dev/commands/smrafiz/claude-supercharger/perf"><img src="https://agentmods.dev/badge/commands/smrafiz/claude-supercharger/perf.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 382 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00382
Opus 5 $0.00000 $0.00191
Sonnet 5 $0.00000 $0.00076
Haiku 4.5 $0.00000 $0.00038

Measured 8d ago against content hash d5c520f8ff4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

perf 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 8d 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.

commands/perf.md · 32 lines

What it actually says

Show hook performance timing report. Options: $ARGUMENTS (e.g. --slow, --days 7)

Run the hook performance profiler and display results.

Step 1 — Run the report

bash ${CLAUDE_PLUGIN_ROOT}/tools/hook-perf.sh $ARGUMENTS

If the command exits with "No hook timing data found", explain:

  • On bash 5+ (zero-fork EPOCHREALTIME clock), hooks slower than ~40ms are recorded automatically — no setup; just use Claude and re-run /perf. Tune with SUPERCHARGER_PERF_THRESHOLD_MS.
  • On bash 3.2 (macOS default — no cheap ms clock) auto-timing is off to avoid a per-hook python fork. Check bash --version; if 3.2, enable full profiling.
  • Full profiling (every hook fire, any bash): touch ${CLAUDE_PLUGIN_DATA}/scope/.profiling, use Claude for a session, re-run /perf, then rm ${CLAUDE_PLUGIN_DATA}/scope/.profiling.

Step 2 — Interpret results

Present the table as-is. Then add a one-line summary:

  • Highlight the slowest hook (highest avg_ms)
  • Note if any hook averages >200ms (flag as candidate for SUPERCHARGER_PROFILE=minimal)
  • Note total overhead per Claude invocation

Step 3 — Suggest action (only if data warrants it)

If total overhead >500ms/call or any hook >200ms avg:

  • Suggest {"profile": "minimal"} in .supercharger.json if the slow hooks are in the minimal skip list
  • Otherwise name the specific hook and suggest disableHooks if it's safe to skip
Changes

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.

  1. 8d ago First seen · 32 lines · 0 tokens per session scan A d5c520f8ff4f

Subscribe to this mod's changes

perf is a command published in the GitHub repository smrafiz/claude-supercharger (11 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 382 tokens. 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 2026-08-30.