Security Audit Skill
Cloudflare's security-audit skill — turns your coding agent into a multi-phase auditor with independently verified findings, MIT
improve is an open-source dev tools project by shadcn (shadcn/improve on GitHub). It has 11,400 GitHub stars and 460 forks, is released under the MIT license, and was last updated on GitHub on 12 September 2026.
The audit skill from shadcn — your best model audits the codebase, cheaper models execute the plans, MIT
Add it with the Skills CLI — it works in any agent that supports the Agent Skills format.
Open your agent in the repo and run /improve for the full audit, or /improve quick for a cheap pass.
Reply with the findings you want — plans land in plans/, one file each, with an index and priority order.
Any agent or human can execute a plan, or let the skill dispatch one and review the work.
Correctness, security, performance, test coverage, tech debt, dependencies, DX, docs and direction — each finding with file:line evidence.
The advisor re-reads every cited location itself, so false positives get dropped before you see them.
Self-contained specs with exact paths, code excerpts, verified commands and machine-checkable done criteria.
execute runs a cheaper model in an isolated worktree and reviews the diff; reconcile refreshes the backlog.
The skill only writes to plans/ and never runs commands that mutate your working tree.
Add improve with the Skills CLI.
npx skills add shadcn/improveFull audit with prioritised findings, or quick for hotspots only.
/improveDispatch a cheaper executor for a plan and get a verdict back.
/improve execute 001Two more from the same shelf: Security Audit Skill — Cloudflare's security-audit skill, and Codex Security — OpenAI's security scanner for Codex. Browse every Dev Tools tool in the catalogue to compare the category.
An agent skill that audits a codebase and writes self-contained implementation plans for other agents (or humans) to execute.
No — it only writes to plans/. Execution happens in isolated worktrees, and merging stays your decision.
Any agent that supports the Agent Skills format; plans are plain Markdown, so anyone can pick them up.
It judges what is worth doing, not just what is wrong — findings are prioritised by leverage (impact ÷ effort, weighted by confidence).
Yes — MIT.
Cloudflare's security-audit skill — turns your coding agent into a multi-phase auditor with independently verified findings, MIT
OpenAI's security scanner for Codex — find, validate and patch vulnerabilities from the CLI, SDK or GitHub Action, Apache-2.0
The open source coding agent
Claude Code skill: four-phase plan hardening (recon, interrogate, Codex adversarial review, cross-model build & inspection) — two AI models harden your plan …
LM Evaluation Harness — EleutherAI framework for few-shot evaluation of language models across many tasks, MIT
Portkey AI Gateway — route to 1,600+ AI models through one fast API, with fallbacks and guardrails, MIT
The most-starred other Dev Tools projects in the LibreAI catalogue — the realistic shortlist if improve is not the right fit.
The open source coding agent
The model-definition framework behind modern AI — thousands of pretrained transformers for text, vision, and audio.
Anthropic's agentic coding tool that lives in your terminal and works across your whole codebase
Cross-platform desktop all-in-one manager for Claude Code, Codex, OpenCode and other coding agents
OpenAI's lightweight coding agent that runs locally in your terminal
Nearby Dev Tools projects in the catalogue, closest in stars to improve — keep exploring the shelf either side of it.
Expose your FastAPI endpoints as Model Context Protocol tools - with authentication - in a few lines of code.
ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly wit…
OpenAI's security scanner for Codex — find, validate and patch vulnerabilities from the CLI, SDK or GitHub Action, Apache-2.0
One Rust CLI for every LLM: shell assistant, chat REPL, RAG, tools and agents across 20+ providers.
Code-search MCP for Claude Code: make your entire codebase the context for any coding agent.
A codebase knowledge graph that makes Claude Code, Cursor, Codex and Gemini faster, cheaper and repo-aware.
Free and open — grab the source, star the repo, and start creating.