Radar / AI coding tools / Claude Code Mods

Claude Code Mods

Anthropic launched mods on Oct 1: small TypeScript functions that hook into Claude Code's agent events to rewrite prompts, block or retry tool calls, approve permissions, redact secrets, and render custom UI; they ship inside plugins and install via /plugin in the CLI or desktop app.

new launchcoding · ideJEV traction 0.68anthropics/claude-code · 0 ★added 2026-10-02

Open Claude Code Mods →View on the radar

Why it matters

Mods open Claude Code's core agent loop and interface to developers for the first time — even Anthropic's own /diff and AGENTS.md support now ship as replaceable mods, turning the coding agent into a programmable platform.

What you could build with it

An indie developer could ship a safety mod bundle for engineering teams that intercepts risky shell commands before the agent runs them, showing exactly which files would change and requiring a one-tap approval — turning the coding agent into a safer pair programmer for shared production repos.

Does it hold up?

Early but concrete: third-party developers had already shipped working mods on the early-access API before launch day — usage dashboards, secret redactors, CI/PR trackers, even games above the prompt — and the awesome-mods scanner validates them against Claude Code 2.1.287. The consistent caution across coverage is that mods run unsandboxed with full machine access, so trust in the source is the whole story.

Built with Claude Code Mods

Claude Code Mods: Rewrite Behavior, Build Custom UIsarticle · Medium walkthrough quoting the official definition of mods and the launch examples Token Weather and Blast Radius, with notes on the unsandboxed trust model.
You Can Now Change How Claude Code Works. Here Are 5 Mods.article · Hands-on roundup of five working mods (Token Weather, Blast Radius, Replay Theater, Diff, AGENTS.md support) matched to everyday jobs, with a video install walkthrough.
Are Claude Code Mods Sandboxed? What They Can Accessarticle · In-depth explainer on the unsandboxed security model: mods run with the agent's full machine access, plus the built-in sec-default guardrail for Teams and Enterprise plans.
Arunjay4213/claude-modsgithub · 3 ★ · Three session trackers and a budget guard for Claude Code built as mods (context-lens, quota-meter, token-ledger, budget-guard); pinned live figures above the prompt plus pane commands, built on the early-access function-hooks API.
karanb192/awesome-claude-code-modsgithub · 69 ★ · Curated catalog of 359 mods across 373 repos with an automated security-footprint scanner: every row lists the events a mod hooks and the access it can reach, refreshed nightly against Claude Code 2.1.287.

Learn more

official docs →

First spotted on article: source.

More AI coding tools

mattpocock/skills: Skills for Real EngineersMatt Pocock's open collection of production agent skills, published straight from his .agents directory - 272k stars…coding · JEV 0.75Pi.dev adds MCP to core: 'You Said No MCP'Pi.dev reverses its public no-MCP stance, integrating Model Context Protocol into the core of its agentic coding…coding · JEV 0.71ZCode: Z.ai's Apache-2.0 open-source coding-agent harness, open-sourced 2026-09-21Z.ai's official coding-agent harness, an Electron desktop app plus browser interface, terminal agent and agent runtime…coding · JEV 0.7CodeGraphPre-indexed, auto-syncing Rust-kernel code knowledge graph for Claude Code, Codex, Cursor, OpenCode, Hermes Agent and…coding · JEV 0.69opencodexUniversal provider proxy for OpenAI Codex and Claude Code: use any LLM with Codex CLI, App, SDK, and Claude Code.coding · JEV 0.69 Whiteboard: open-source canvas IDE for human-agent software designAn open-source, MIT-licensed desktop app where humans and agents architect software together on a shared canvas. The…coding · JEV 0.62

Get the week's best AI launches, plus 3 ideas worth building

One email every Saturday. Ranked by traction, not hype. Free.