by alanhuangyoo
Taking the pi coding agent to Claude Code-level performance: 0.539 → 0.773 pass@1 on Terminal-Bench 2.1 with the same self-hosted 27B model, by re-engineering the agent.
# Add to your Claude Code skills
git clone https://github.com/alanhuangyoo/cruxGuides for using ai agents skills like crux.
Last scanned: 10/6/2026
{
"issues": [
{
"type": "npm-audit",
"message": "@earendil-works/gondolin: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "@vitest/coverage-v8: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@vitest/mocker: Vitest: Path Traversal / Arbitrary File Read via @vitest/mocker Redirect Mock",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "brace-expansion: brace-expansion: Quadratic-time expansion of the `{a},b}` rewrite causes CPU denial of service",
"severity": "high"
},
{
"type": "npm-audit",
"message": "braces: braces vulnerable to stack-exhaustion denial of service through deeply nested patterns",
"severity": "high"
},
{
"type": "npm-audit",
"message": "fast-glob: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "micromatch: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "node-forge: node-forge RSA PKCS#1 v1.5 signature verification accepts extra nested DigestAlgorithm elements",
"severity": "high"
},
{
"type": "npm-audit",
"message": "shelljs: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "shx: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "source-map-js: source-map-js allows event-loop denial of service through indexed source-map section offsets",
"severity": "high"
},
{
"type": "npm-audit",
"message": "undici: undici vulnerable to Denial of Service via unhandled error in WebSocket permessage-deflate decompression",
"severity": "high"
},
{
"type": "npm-audit",
"message": "vitest: Vulnerability found",
"severity": "medium"
}
],
"status": "WARNING",
"scannedAt": "2026-10-06T11:02:28.628Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how crux compares with popular alternatives.
crux is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by alanhuangyoo. Taking the pi coding agent to Claude Code-level performance: 0.539 → 0.773 pass@1 on Terminal-Bench 2.1 with the same self-hosted 27B model, by re-engineering the agent. It has 187 GitHub stars.
crux returned warnings in SkillsLLM's automated security scan. It has no critical vulnerabilities, but review the flagged issues in the Security Report section before adding it to your workflow.
Clone the repository with "git clone https://github.com/alanhuangyoo/crux" and add it to your Claude Code skills directory (see the Installation section above).
crux is primarily written in TypeScript. It is open-source under alanhuangyoo on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh crux against similar tools.
No comments yet. Be the first to share your thoughts!
Requires a passing catalog security scan.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM lists this project for discovery and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
| Agent | Terminal-Bench 2.1 pass@1 |
|---|---|
| Crux | 0.773 0.793 on a rerun |
| Claude Code, same model | 0.730 |
| pi, upstream | 0.539 |
Self-hosted Qwen3.8-27B, identical weights for every agent · 89 tasks · pass@1 over whole runs.
All changes are in the agent layer; the model is untouched.
benchmark/ holds the harness behind these numbers: it runs the
agent in task containers via harbor, classifies every trial's outcome, and
compares versions task by task with a paired sign test.
cd benchmark && uv sync
harbor run --dataset terminal-bench/terminal-bench-2-1 \
--agent crux.pi_agent:CruxPiAgent --model openai/<model>
Built on pi by Earendil Works
(earendil-works/pi). Licensed as
upstream; see LICENSE.