hal-grammar-check
vinta/hal-9000
Grammar-check your prompt as you type, shown above the prompt box
69 mods
vinta/hal-9000
Grammar-check your prompt as you type, shown above the prompt box
vinta/hal-9000
Automatically name each session and rename it as the conversation evolves
vinta/hal-9000
Suggests the ! shell command Claude's last reply asks you to run, Tab to take
vinta/hal-9000
Show each subagent's status, model, effort, and context usage in its agent row
xiaolai/claude-rich-terminal
Mermaid diagrams drawn inside Claude Code replies, and a truecolor status line under the prompt with a Token Weather forecast of the context window.
superfly/sprites-claude-plugin
Use Sprites from Claude Code to create, inspect, and operate remote isolated development environments.
superfly/sprites-claude-plugin
Manage Fly.io apps, Machines, volumes, secrets, Managed Postgres, and Sprites through the hosted Fly MCP server.
tobinsouth/fortune-cookie-mod
/fortune cracks open a fortune cookie: one line of wisdom for your coding session, shown in the transcript and as a toast.
anthropics/claude-code
The diff pane as a plugin: /diff opens the session's uncommitted changes beside the transcript, file by file with their hunks, refreshed as Claude edits and runs commands; the first edit opens it where the terminal is wide enough, and a file's ask button rides its hunks on the next prompt.
anthropics/claude-code
AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and...
anthropics/claude-code
Security default for organizations: seated outermost, it keeps the organization's classic hooks, prompt content, settings, tool policy and pinned environment out of reach of the plugins a person installs, and keeps those plugins from running the model's call before it is allowed; two managed options add a control: allowManagedModsOnly limits mods to the organization's, and forceHotReloadPrompt...
anthropics/claude-code
Plugin analytics: hooks $.telemetry's two events, so a plugin logs an event or marks a feature's use as a first-party row, sent in batches with the session's own credential.
anthropics/claude-code
Refuses a shell, file, web fetch or MCP call that holds the signed-in account's email address beside a word that declares who is calling, so the address does not go out as a client's identity, and refuses a user-tier plugin's own read of the session's identity.
anthropics/claude-code
Draws charts in the transcript: a chart tool for Claude, and automatic charts for MCP results that are metrics over time
anthropics/claude-code
For organizations under HIPAA: refuses a plugin's or a settings hook's own call to an MCP or connector tool that an administrator blocked, or to any tool, file or process where a managed deny rule covers the call, unless it is the organization's.
anthropics/claude-plugins-official
Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page report, specialist agents, and an optional live progress pane (early access).
anthropics/claude-plugins-official
An example plugin to read, copy and change: thirty-eight animated backdrops behind the chat in the desktop app, with frosted-glass panels: one per project or per session. /custom-theme list names them. Fireworks go off over the theme when Claude says "merged"; /fireworks sets them off by hand.
anthropics/claude-plugins-community
After each turn, suggests up to three next prompts above the input. Press 1, 2 or 3 to put one in the prompt box as a draft you can edit, 0 to dismiss.
anthropics/claude-code-playground
Holds risky shell commands (rm -rf, git reset --hard, git clean, force push, migrations) and shows what they would change, with Proceed and Cancel buttons.
anthropics/claude-code-playground
Replay Theater: step through the file edits Claude made in the last turn, one diff at a time.
anthropics/claude-code-playground
A live forecast of the context window, drawn above the prompt: a weather icon, the fill percentage, and a chart of the last turns.
No tracking cookies, no third-party scripts. How we handle data