What is performance-review?

A performance-improvement workflow for a Rust command-line search tool. It measures a release build, finds slow steps, and plans possible optimizations.

Use it to benchmark searches, investigate steps taking over one second, review optimization proposals, and measure implemented changes.

It provides a measured starting point and checks whether each proposed change actually makes the program faster while preserving compatibility and repeatable results.

How probelabs/probe configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to probelabs/probe. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/probelabs/probe/main/.claude/commands/performance-review.md

Clone the repo

git clone --depth 1 https://github.com/probelabs/probe

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/probelabs/probe/performance-review/github.svg)](https://agentmods.dev/commands/probelabs/probe/performance-review)

Your own site

<a href="https://agentmods.dev/commands/probelabs/probe/performance-review"><img src="https://agentmods.dev/badge/commands/probelabs/probe/performance-review/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/probelabs/probe/performance-review"><img src="https://agentmods.dev/badge/commands/probelabs/probe/performance-review.svg" alt="Reviewed on agentmods" width="80" 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 263 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00263
Opus 5.5	$0.00000	$0.00105
Sonnet 5.5	$0.00000	$0.00053
Haiku 4.5	$0.00000	$0.00026

Measured 2mo ago against content hash acab872f44ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

performance-review 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 2mo 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.

.claude/commands/performance-review.md · 16 lines

What it actually says

You goal is to measure and improve performance.

First run cargo build --release and remember the current performance: DEBUG=1 ./target/release/probe search "yaml workflow agent multi-agent user input" ~/go/src/semantic-kernel/ --max-tokens 10000 2>/dev/null | sed -n '/=== SEARCH TIMING INFORMATION ===/,/====================================/p'

Print it to the user.

Now that you have a baseline, find all the steps which take more then 1 second, and run the seaprate @architecture-agent for each, to plan if we can significantly improve performance. For each suggestion measure confidence. If confidence is high, add it to the detailed plan, if not, say that it is already performance enough.

Once you went though all the steps and build solid plan, I want you to start implementing it in a separate agent. But always explicitly ask user before each next implementation.

Each change should be measured, and compared with our baseline. You can add more debugging to search timing information, or making it more detailed if needed. Once each change implemented, it should be commited as a separate commit.

We do care about backward compatibility, about determenistic outputs as well. Be careful. Validate each change by re-running all the tests..

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.

2mo ago First seen · 16 lines · 0 tokens per session scan A acab872f44ca

Subscribe to this mod's changes

performance-review is a command published in the GitHub repository probelabs/probe (736 stars, last pushed 9d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 263 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.

Debugging ai ai-coder ast cli code-search search-engine

performance-review next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
performance-reviewprobelabs/probe	Command	736	9d ago	Apache-2.0	A	0	Claude Code
searchdvcdsys/code-index	Command	31	3d ago	MIT	A	16	Claude Code
defdvcdsys/code-index	Command	31	3d ago	MIT	A	17	Claude Code
refsdvcdsys/code-index	Command	31	3d ago	MIT	A	17	Claude Code
definitionHelweg/open-codebase-index	Command	230	2d ago	MIT	A	10	Claude Code
explain-errorGoldziher/ai-rulez	Command	167	yesterday	MIT	A	15	Claude Code
securityajitpratap0/GoSQLX	Command	124	2d ago	Apache-2.0	A	21	Claude Code

probe: Command for Claude Code