ANC 100 — Agent-Native CLI Leaderboard

Automated agent-readiness scores for real CLI tools, scored against the eight principles. See the methodology for how scores, audience signals, and audit profiles work.

98 audited tools in the corpus.

Agent-optimized only

#	Tool	Description	Tier	Lang	Score	Principles
1	anc	Audit CLI tools against the agent-native standard	notable	Rust	100	8/8
2	watchexec	Execute commands in response to file modifications	workhorse	Rust	88	5/8
3	miniserve	Serve files over HTTP right now	workhorse	Rust	85	4/8
4	bat	A cat clone with syntax highlighting and Git integration	workhorse	Rust	84	4/8
5	delta	A syntax-highlighting pager for git, diff, grep, and blame output	workhorse	Rust	84	4/8
6	ripgrep	Recursively search directories for a regex pattern	workhorse	Rust	82	3/8
7	fd	A simple, fast, and user-friendly alternative to find	workhorse	Rust	82	3/8
8	bandwhich	Terminal bandwidth utilization tool	workhorse	Rust	82	3/8
9	just	A command runner for project-specific tasks	workhorse	Rust	82	3/8
10	lsd	The next gen ls command	workhorse	Rust	81	4/8
11	mise	Dev tools, env vars, task runner	workhorse	Rust	80	4/8
12	make	Build automation tool that reads Makefiles	workhorse	C	80	3/8
13	procs	A modern replacement for ps written in Rust	workhorse	Rust	79	3/8
14	tealdeer	A very fast implementation of tldr in Rust	notable	Rust	79	3/8
15	sd	Intuitive find-and-replace CLI (sed alternative)	workhorse	Rust	79	3/8
16	ruff	An extremely fast Python linter and code formatter	workhorse	Rust	79	3/8
17	trivy	Find vulnerabilities, misconfigurations, and secrets in containers and code	workhorse	Go	78	3/8
18	hyperfine	A command-line benchmarking tool	workhorse	Rust	77	3/8
19	gitui	Blazing fast terminal UI for git	workhorse	Rust	77	4/8
20	eza	A modern alternative to ls	workhorse	Rust	77	3/8
21	jq	Command-line JSON processor	workhorse	C	77	3/8
22	xh	Friendly and fast tool for sending HTTP requests	workhorse	Rust	76	2/8
23	rclone	rsync for cloud storage	workhorse	Go	76	3/8
24	jnv	Interactive JSON filter using jq	notable	Rust	76	3/8
25	opencode	Open source coding agent for the terminal	agent	TypeScript	76	3/8
26	actionlint	Static checker for GitHub Actions workflow files	workhorse	Go	76	3/8
27	xr	Fast, ergonomic CLI for the X (Twitter) API	notable	Rust	76	2/8
28	pixi	Fast cross-platform package manager built on Conda	workhorse	Rust	75	3/8
29	lazygit	Simple terminal UI for git commands	workhorse	Go	75	3/8
30	mods	AI on the command line	agent	Go	75	3/8
31	jj	A Git-compatible VCS that is both simple and powerful	workhorse	Rust	75	2/8
32	typst	A markup-based typesetting system that is powerful and easy to learn	workhorse	Rust	75	2/8
33	gitleaks	Find secrets in code with Gitleaks	workhorse	Go	75	3/8
34	docker	The Docker CLI	workhorse	Go	74	2/8
35	dust	A more intuitive version of du in Rust	workhorse	Rust	74	2/8
36	ast-grep	Structural search and replace for code using AST patterns	workhorse	Rust	74	3/8
37	codex	Lightweight coding agent that runs in your terminal	agent	Rust	74	2/8
38	zoxide	A smarter cd command	workhorse	Rust	74	2/8
39	curl	Command-line tool for transferring data with URLs	workhorse	C	73	3/8
40	git-cliff	A changelog generator that follows Conventional Commit specifications	workhorse	Rust	73	2/8
41	bottom	A cross-platform graphical process/system monitor	workhorse	Rust	73	3/8
42	fzf	A command-line fuzzy finder	workhorse	Go	73	3/8
43	cargo-binstall	Binary installation for Rust projects	workhorse	Rust	73	3/8
44	xai-grok-build	xAI's Grok Build TUI — agentic coding CLI for Grok models	agent	Rust	73	2/8
45	cf	Cloudflare's beta unified CLI (Technical Preview); rebuilt for agent-first ergonomics	workhorse	TypeScript	73	2/8
46	uv	An extremely fast Python package and project manager	workhorse	Rust	73	2/8
47	goose	An open-source, extensible AI agent that goes beyond code suggestions	agent	Rust	73	2/8
48	nushell	A new type of shell	notable	Rust	73	4/8
49	cmake	Cross-platform build system generator	workhorse	C++	73	3/8
50	wrangler	CLI for Cloudflare Workers	workhorse	TypeScript	72	2/8
51	age	A simple, modern, and secure file encryption tool	workhorse	Go	72	3/8
52	tokei	Count your code, quickly	workhorse	Rust	72	2/8
53	scc	Fast accurate code counter with complexity calculations	workhorse	Go	72	2/8
54	rsync	Fast, versatile file copying and synchronization tool	workhorse	C	72	2/8
55	shellcheck	Static analysis tool for shell scripts	workhorse	Haskell	72	3/8
56	qmd	Local hybrid search (BM25 + vector + LLM rerank) for personal knowledge bases	notable	TypeScript	72	2/8
57	biome	Formatter and linter for JavaScript, TypeScript, JSON, and CSS	workhorse	Rust	72	3/8
58	yazi	Blazing fast terminal file manager	workhorse	Rust	72	3/8
59	deno	A modern runtime for JavaScript and TypeScript	workhorse	Rust	72	3/8
60	yq	Portable command-line YAML, JSON, XML, CSV, TOML, and properties processor	workhorse	Go	71	2/8
61	pastel	A command-line tool to generate, analyze, convert, and manipulate colors	notable	Rust	71	2/8
62	bird	Rust CLI for the X (Twitter) API	notable	Rust	71	1/8
63	glow	Render markdown on the CLI	workhorse	Go	71	2/8
64	gemini-cli	Open-source AI agent that brings Gemini directly into the terminal	agent	TypeScript	71	2/8
65	terraform	Infrastructure as code, safely and predictably	workhorse	Go	71	2/8
66	doggo	Command-line DNS client for humans	notable	Go	71	2/8
67	files-to-prompt	Concatenate a directory full of files into a single prompt for LLMs	notable	Python	71	3/8
68	claude-code	Anthropic's agentic coding tool for the terminal	agent	TypeScript	70	3/8
69	pandoc	Universal markup converter	workhorse	Haskell	70	2/8
70	vhs	Your CLI home video recorder	notable	Go	70	2/8
71	broot	A new way to see and navigate directory trees	workhorse	Rust	70	4/8
72	ollama	Get up and running with large language models locally	agent	Go	70	2/8
73	starship	The minimal, blazing-fast, and infinitely customizable prompt for any shell	workhorse	Rust	70	2/8
74	navi	An interactive cheatsheet tool for the command-line	notable	Rust	70	3/8
75	git	Distributed version control system	workhorse	C	69	2/8
76	miller	Like awk, sed, cut, join, and sort for name-indexed data (CSV, JSON, etc.)	workhorse	Go	69	3/8
77	atuin	Magical shell history	notable	Rust	69	2/8
78	llm	Access large language models from the command-line	notable	Python	68	3/8
79	nvidia-smi	NVIDIA GPU monitoring and management interface	workhorse	C	68	2/8
80	gh	GitHub's official command-line tool	workhorse	Go	68	3/8
81	gum	A tool for glamorous shell scripts	notable	Go	68	1/8
82	sqlite-utils	CLI utility and library for manipulating SQLite databases	notable	Python	68	2/8
83	datasette	An open-source multi-tool for exploring and publishing data	notable	Python	67	3/8
84	act	Run your GitHub Actions locally	workhorse	Go	67	2/8
85	supabase	Manage Supabase projects from the CLI	workhorse	Go	66	2/8
86	flyctl	Command-line tools for Fly.io services	workhorse	Go	66	2/8
87	direnv	Unclutter your .profile with per-directory environment variables	workhorse	Go	66	2/8
88	aws-cli	Universal command-line interface for Amazon Web Services	workhorse	Python	66	3/8
89	xsv	A fast CSV command-line toolkit	workhorse	Rust	65	1/8
90	kubectl	Kubernetes command-line tool	workhorse	Go	65	3/8
91	bun	Incredibly fast JavaScript runtime, bundler, test runner, and package manager	workhorse	Zig	65	2/8
92	cosign	Code signing and transparency for containers and binaries	workhorse	Go	64	2/8
93	cursor	AI code editor (VS Code fork) with diff/merge/goto CLI launcher	agent	TypeScript	63	2/8
94	helm	The Kubernetes package manager	workhorse	Go	63	2/8
95	ffmpeg	Record, convert, and stream audio and video	workhorse	C	63	2/8
96	dasel	Select, put, and delete data from JSON, TOML, YAML, XML, and CSV	workhorse	Go	60	1/8
97	shell-gpt	A command-line productivity tool powered by AI large language models	agent	Python	58	2/8
98	tmux	Terminal multiplexer	workhorse	C	54	2/8

Claim the badge

Tools at or above 70% can embed the agent-native badge on their README — a live link to their scorecard, not a static stamp. 74 of 98 listed tools currently qualify.

Methodology

Every score is the output of anc audit <binary> against a real CLI tool. The score column is the behavioral-layer compliance score: requirement checks, credit-weighted by outcome (a met requirement counts full, a missed SHOULD or MAY counts half); the principles met column counts how many of the eight principles have every check passing. The audience classification — when present — is informational, not authoritative; the per-tool page's evidence list is the ground truth.

For the full explanation of scoring, audience classification, audit profiles, and how to request a re-score, see the methodology page.

To reproduce any row locally, install anc and run anc audit <binary>.