claudeers.
// Claude Skills

blazing-rust

A Rust performance skill for Claude Code and Codex

Install with your AI

Paste into Claude Code, Cursor, or any agent — it reads the repo and wires the tool into your project.

Install and set up blazing-rust (claude-skill project) into my current project.
Found on https://claudeers.com/blazing-rust
Repo: https://github.com/painhardcore/blazing-rust
Homepage/docs: —
Detected install method: claude-skill → # copy this skill into .claude/skills/blazing-rust/
Category: skills. Platforms: cli.
Read the repo's README for exact setup and env vars, then install it and wire it into my project.

Claudeers Health Verdict:
unknown; community-verified: false. Confirm the source before running anything.
// or install directly (claude-skill)
# copy the skill dir into your project:
# .claude/skills/blazing-rust/   (or ~/.claude/skills/blazing-rust/ for all projects)
// or clone
git clone https://github.com/painhardcore/blazing-rust

// compatibility

Platformscli
Operating systems—
AI compatibilityclaude
LicenseMIT
Pricingopen-source
LanguageRust

Get your FREE $2.50 API credits to access TickAtlas financial data ↗

Blazing Rust

A Rust performance skill for Claude Code, Codex, and other agents that support Agent Skills.

The agent measures a baseline, finds the bottleneck, and pushes it toward the hardware limit one measured change at a time. It stops at lines it will not cross on its own: changed behavior, unsound unsafe, weaker security, new threads in library code, and new dependencies or build settings. Faster options beyond those lines are reported with their measured gain. It covers allocations, data structures, memory layout, async code, SIMD, parallelism, and compiler settings.

Results

Four tasks, each run with and without the skill on the same prompt, with no user instructions loaded. 27 checks cover:

  • measuring before editing;
  • correct results;
  • not crossing the lines above;
  • pushing past the first win;
  • not editing code when only asked why it is slow.

Checks passed with and without the skill: Opus 82% to 100%, Sonnet 76% to 96%, Haiku 79% to 97%

ModelChecks passed with the skillWithout the skill
Claude Opus 5.5100%82%
Claude Sonnet 5.5, high effort96%76%
Claude Haiku 5.597%79%

What changed with the skill, on Opus:

TaskWith the skillWithout the skill
Speed up an allocation-heavy log parser46x faster on one thread. It keeps the collision-resistant hasher, adds no threads, and reports that 4 threads would give another 3.7x.32x, using a weak hasher on untrusted input and threads inside a library function
Rewrite a byte counter with SIMD on stable Rust14x faster with no unsafe. It wrote hand-written NEON code, measured it, and did not ship it because the safe version was as fast.15x with 10 unsafe blocks, never compared to a safe version
Explain why an event merge is slowConfirms both O(n²) loops at small sizes, extrapolates the full case, and edits nothingRetries the minute-long full-size run until the process is killed
Speed up a checksum that is already vectorizedKeeps the original code and shows it is within about 20% of the L1-cache limit and near memory bandwidth beyond itAlso keeps it, but does not say how much headroom is left

Sonnet with the skill produced safe 12–19x speedups at about a fifth of Opus's cost. With the skill, runs take roughly twice the time and tokens of runs without it, because the agent measures more. These are single runs on an Apple M1, so treat individual numbers as rough. The test cases are in evals/.

Install

With Node.js 22.20 or later, run this from the project where you want the skill:

npx skills add painhardcore/blazing-rust --skill blazing-rust

Choose your agent when prompted, or select it with -a:

# Claude Code
npx skills add painhardcore/blazing-rust --skill blazing-rust -a claude-code

# Codex
npx skills add painhardcore/blazing-rust --skill blazing-rust -a codex

Add -g to install for all your projects. The skills CLI also supports Cursor, OpenCode, and other agents.

To install from a local checkout, replace painhardcore/blazing-rust with its absolute path.

Install without Node.js

Clone this repository, or use your existing checkout:

git clone https://github.com/painhardcore/blazing-rust.git
cd blazing-rust

Choose the destination for your agent:

AgentAll your projectsOne project
Claude Code~/.claude/skills/blazing-rust<project>/.claude/skills/blazing-rust
Codex~/.agents/skills/blazing-rust<project>/.agents/skills/blazing-rust

For example, install for Claude Code:

skill_dir="$HOME/.claude/skills/blazing-rust"
mkdir -p "$skill_dir"
cp -i SKILL.md LICENSE "$skill_dir/"
mkdir -p "$skill_dir/references"
cp -i references/techniques.md "$skill_dir/references/"

For Codex, set skill_dir="$HOME/.agents/skills/blazing-rust" instead. For other agents, use their skills directory. Copy SKILL.md, LICENSE, and references into a folder named blazing-rust.

See the Claude Code and Codex documentation for supported skill locations.

Use

Start a new agent session after installation. Invoke the skill directly:

Claude Code:

/blazing-rust Investigate why parsing large files is slow. Measure a baseline, optimize the bottleneck, and verify the result.

Codex:

$blazing-rust Investigate why parsing large files is slow. Measure a baseline, optimize the bottleneck, and verify the result.

The agent can also load the skill when you ask about Rust performance. Give it representative inputs, a target metric, and any deployment constraints.

Steer it from the prompt

By default the agent keeps pushing until it meets your target, reaches the hardware limit, or runs out of candidates that stay within its lines. Add a sentence to your prompt to move a line:

DefaultTo change it, say
unsafe is kept only when it beats the best safe version by more than the noise, with a portable fallback and tests"Safe Rust only." or "No unsafe unless it's at least 2x faster."
Library code gets no new threads; the multicore gain is reported"This is a CLI that owns its threads; parallelism is fine."
No new dependencies, build settings, or installed tools"You may add crates." or "You may enable LTO and target-cpu=native; we deploy on one CPU type."
Hashers stay collision-resistant for untrusted keys"Keys are trusted internal IDs."
Pushes toward the hardware limit, even if the code grows"Stop at 2x." or "Target: under 50 ms for 1M lines." or "Keep the code simple."
"Why is X slow?" gets measurements and a diagnosis, with no edits"Explain, then fix it."

The agent tells you the gain it left on the table, so you can rerun with a looser line if that gain is worth it.

The skill uses your project's Rust toolchain and measurement tools. It does not require Criterion or a profiler. When a tool is unavailable, the agent must state what it could not measure.

The technique guide has detailed optimization advice. The agent reads the sections relevant to the workload.

Example: CarryFS

A run on CarryFS produced these changes. The figures come from the commit notes and have not been reproduced independently.

ChangeBeforeAfter
Fixed-size arrays for catalog keys instead of Vec<u8>: lookups for 10,000 files2.69 ms1.94 ms (−28%)
Skip unnecessary Unicode lookups in mixed-Unicode directory reads60.79 ms33.74 ms (−44.5%)
Fast-path ASCII processing34.31 ms21.59 ms (−37.1%)

The key change replaced object.to_be_bytes().to_vec() plus a pushed tag byte with a [u8; 9] array. Another commit cut 14,338 allocator calls per round, but its latency results were within noise, so it claims no speedup.

License

MIT. Copyright 2026 Andrei Iurchenkov.

// faq

What is blazing-rust?

A Rust performance skill for Claude Code and Codex. It is open-source on GitHub.

Is blazing-rust free to use?

blazing-rust is open-source under the MIT license, so it is free to use.

What category does blazing-rust belong to?

blazing-rust is listed under skills in the Claudeers registry of Claude-compatible tools.

7 views
★ 10 stars
unclaimed
updated 8 days ago

// embed badge

blazing-rust on Claudeers
[![Claudeers](https://claudeers.com/api/badge/blazing-rust.svg)](https://claudeers.com/blazing-rust)

// retro hit counter

blazing-rust hit counter
[![Hits](https://claudeers.com/api/counter/blazing-rust.svg)](https://claudeers.com/blazing-rust)

// reviews

// guestbook

0/500

// related in Claude Skills

🔓

An agentic skills framework & software development methodology that works.

// skillsobra/⟨Shell⟩★ 314,126◷ MIT[ claude ]
🔓

Public repository for Agent Skills

// skillsanthropics/⟨Python⟩★ 188,182[ claude ]
🔓

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs,…

// skillsGraphify-Labs/⟨Python⟩★ 149,064◷ MIT[ claude ]
🔓

💫 Toolkit to help you get started with Spec-Driven Development

// skillsgithub/⟨Python⟩★ 148,200◷ MIT[ claude ]
→ see how blazing-rust connects across the ecosystem