automagik-cli: Command for Claude Code

.claude/commands/speed.md

speed is a command for Claude Code from namastexlabs/automagik-cli. It costs 0 tokens per session (3,640 once invoked), scanned A, original, MIT.

A performance-optimisation framework that proposes code changes and verifies them with benchmarks and tests. It keeps each optimisation separately traceable and can revert changes that fail verification.

In plain words
What is it for?
Use it to benchmark optimisation ideas, check correctness, and keep or undo individual performance changes.
Why use it?
It helps distinguish real speed improvements from changes that only appear promising or break existing behaviour.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the TodoWrite tool.

This is namastexlabs/automagik-cli's own configuration. It tells Claude Code how to work on automagik-cli itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything automagik-cli configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/speed/verify_test_coverage.py.

Reuse

Borrowing it

Nothing to install: this file belongs to namastexlabs/automagik-cli. 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/namastexlabs/automagik-cli/main/.claude/commands/speed.md
Clone the repo
git clone --depth 1 https://github.com/namastexlabs/automagik-cli

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.

agentmods badge for speed

README.md
[![agentmods](https://agentmods.dev/badge/commands/namastexlabs/automagik-cli/speed.svg)](https://agentmods.dev/commands/namastexlabs/automagik-cli/speed)
Your own site
<a href="https://agentmods.dev/commands/namastexlabs/automagik-cli/speed"><img src="https://agentmods.dev/badge/commands/namastexlabs/automagik-cli/speed.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 3,640 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 $0.03640
Opus 5 $0.00000 $0.01820
Sonnet 5 $0.00000 $0.00728
Haiku 4.5 $0.00000 $0.00364

Measured 3d ago against content hash 00c1646a0b02, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

speed 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 3d 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/speed.md · 509 lines

How it starts

The opening of the file, as written. The whole thing — 509 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/speed


allowed-tools: Task(), Read(), Write(), Edit(), MultiEdit(), Glob(), Grep(), Bash(), LS(), TodoWrite(), WebSearch(), mcp__zen__, mcp__search-repo-docs__, mcp__ask-repo-agent__, mcp__genie_memory__, mcp__send_whatsapp_message__, mcp__wait__* description: Genie Speed Optimization Framework - AI-assisted performance optimization with generate-and-verify approach

Genie Speed Optimization Framework

Overview

The Genie Speed Optimization Framework is an AI-assisted performance optimization system inspired by Codeflash that follows a "generate and verify" approach. It uses multi-model consensus to generate optimizations, rigorously verifies performance improvements, and maintains code correctness through comprehensive testing.

Core Philosophy

  • Generate and Verify: AI models propose optimizations, empirical benchmarking validates improvements
  • One Commit Per Optimization: Each optimization attempt gets its own commit for traceability
  • Automatic Revert: Failed optimizations are automatically reverted to prevent regressions
  • Multi-Model Consensus: Complex optimizations require agreement from multiple AI models
  • Minimum Runtime Principle: Performance measured using best-of-N runs to minimize noise

Framework Components

1. Benchmarking Infrastructure (scripts/speed/)

  • benchmark_runner.py: Core benchmarking engine with minimum runtime measurement
  • performance_profiler.py: Code profiling and bottleneck identification
  • noise_reduction.py: Statistical techniques for stable performance measurement
  • baseline_manager.py: Manages performance baselines and regression detection

2. Git Automation (scripts/speed/git/)

  • checkpoint_manager.sh: Creates optimization checkpoints and manages branches
  • auto_revert.sh: Automatically reverts failed optimizations
  • commit_automation.py: Handles structured commits with performance metadata
  • conflict_resolver.py: Manages git conflicts during optimization workflows

Read the full file on GitHub · 509 lines

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. 3d ago First seen · 509 lines · 0 tokens per session scan A 00c1646a0b02

Subscribe to this mod's changes

speed is a command published in the GitHub repository namastexlabs/automagik-cli (6 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,640 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 2026-09-04.