linear
omeerdvrn/o-mods
Sidebar of your assigned Linear issues; Start creates a git worktree and begins implementing the issue.
6,360 mods
omeerdvrn/o-mods
Sidebar of your assigned Linear issues; Start creates a git worktree and begins implementing the issue.
omeerdvrn/o-mods
Pick a role for Claude on this machine (UI/UX, Backend, Dev, QA, Docs, PM); edits and shell commands outside the role are denied, and the Claude crab dressed for the role shows under the prompt.
omeerdvrn/o-mods
Live CI status of the current branch's pull request above the prompt, or of any PR you pin with /pr-status . Detects GitHub, GitLab, Gitea/Forgejo, Bitbucket and Azure DevOps.
omeerdvrn/o-mods
Animated pixel scenes above the prompt while Claude works, a random one each time: night drive, rainy window, fish tank, space flight, lo-fi room, campfire, ocean sunset, matrix rain, usage weather. Confetti when tests pass, a rocket on push, and a companion crab that acts out what Claude does. Drawn, no images.
omeerdvrn/o-mods
The input bar, smarter: your Linear tickets in the typeahead as you type an id, live highlighting (tickets, paths, @mentions, secrets in red), and ;;snippets that expand as you type (;;mmi, ;;plan, ;;review...), and previews of pasted images above the input.
omeerdvrn/o-mods
Routes every task to a worker subagent on the right model tier (Haiku, Sonnet, Opus) by rules you own, tracks it in a registry, and shows each model as a Claude crab in a status sidebar. Works with Superpowers: it plans, the router executes.
omeerdvrn/o-mods
Color themes for Claude Code (Catppuccin, Dracula, Nord, Tokyo Night, Gruvbox, Rosé Pine and more). Each new session takes the next theme, so sessions are easy to tell apart; /themes picks or pins one.
omeerdvrn/o-mods
Shows your 5-hour and weekly plan limits, used or remaining, and the session's git branch or worktree under the prompt.
omeerdvrn/o-mods
Your Claude Code usage on this machine as a receipt: total tokens, prompts, sessions, issues closed, daily activity, and tokens by project and model. Opens with /usage-stats.
vumichien/claude-code-mods-kit
After a turn that edited files or ran commands, Haiku lists the choices Claude made that you did not state. Mark each right or wrong, add a note, and send the corrections back as one prompt. Starts off: /assumption-check on turns it on
vumichien/claude-code-mods-kit
A band above the prompt with what fills the context window, by category, a countdown to when the prompt cache expires, and a Compact button. Starts off: /context-meter on turns it on
vumichien/claude-code-mods-kit
Notices when Claude marks a task done while code it changed has not been tested since, and tells Claude and you; a band shows the last test run. It warns, it never blocks. Starts off: /done-gate on turns it on
vumichien/claude-code-mods-kit
Park an idea while Claude works, without interrupting it: /idea , or the shelf's own box. Ideas are kept per project across sessions, and Send puts one in the prompt box when you are ready. Starts off: /idea-shelf on turns it on
vumichien/claude-code-mods-kit
A band above the prompt with how far your plan file is (phases and steps done, what is in progress, what is next) and Claude's own task list, kept current as files change. Starts off: /plan-meter on turns it on
vumichien/claude-code-mods-kit
An Enhance button above the prompt: Haiku rewrites your draft to name the skills that fit, the questions Claude should ask first and what done looks like. It never submits; Send does. Starts off: /prompt-enhancer on turns it on
vumichien/claude-code-mods-kit
Hides secrets in tool results before Claude reads them: the secret values of every .env and .env.* from your session's folder up to the drive root, and anything that looks like a secret (KEY=VALUE under a secret name, passwords in URLs, private keys, JWTs, AWS keys, Kubernetes Secrets); tells Claude how to use them without printing them
vumichien/claude-code-mods-kit
See your other Claude Code sessions from this one: which are working, which wait for you, which are done, and which share this folder. Each session writes a small heartbeat file; nothing else is shared. Starts off: /session-monitor on turns it on
galElmalah/claude-mods
Mermaid diagrams in Claude Code: every mermaid block Claude writes is drawn as box art, in colour, right where the fence was in the transcript. Needs function hooks (early access) and an interactive terminal.
galElmalah/claude-mods
A prompt typed while Claude is working is held in a stack above the prompt instead of landing in the running turn, and sent once the turn ends. Reorder the stack, edit a row in place, send one first, remove one, flush the lot. Needs function hooks (early access) and an interactive terminal.
Anerco/claude-code-effort-cycle
Change Claude Code's effort level per agent: Ctrl+↑ and Ctrl+↓ step the main thread or the subagent in view, shown as a colored meter in the footer (‹ › to click on hover) and in the tasks list's subagent rows
danyuchn/claude-mods
Passive 50-minute prompt-cache reminder with a keyboard/mouse panel: keep warm, ping once, or compact, with live cost estimates.
danyuchn/claude-mods
Masks sensitive names, orgs and secrets in the transcript for screen sharing; /mask toggles, click a mask to reveal
ugglr/claude-token-monster
A pixel-art monster in a side pane that eats tokens and shows context, limits and activity at a glance
oliverow/catch-me-up
A side pane with a live catch-up summary of your Claude Code session: why it started, what was done, where things stand, and what needs you
No tracking cookies, no third-party scripts. How we handle data