arc: Arc for macOS without sign-in, with Arc's services blocked and tools for coding agents

by CryogenicPlanet · Agent Tool · ★ 64

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

How to install arc

git clone https://github.com/CryogenicPlanet/arc.git
bun tools/build-mod.ts   # builds ArcMod and puts it in /Applications

Taken from the project's README on GitHub. Check the security audit before running it.

Security audit verdict: SAFE · quality 66/100

None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

Quick Facts

Stars64
Forks6
LanguageTypeScript
CategoryAgent Tool
Quality Score66/100
Open Issues2
Last Updated2026-10-26
Created2026-10-13
Platformsnode
Est. Tokens~17k

About arc

ArcMod ArcMod is a modified copy of the Arc browser for macOS that you can use without an Arc account. Arc's own services are blocked, it's a little lighter, and coding agents (Codex, Claude Code) get browser tools of their own. Work in progress. This is an experimental mod I use day to day. Expect rough edges. Known problems are tracked in the pinned status issue.

Compatible Skills

These tools work well together with arc for enhanced workflows:

  • depwire — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools