All mods
3,717 mods. Every one passed the check.
- pins 0.1.0 Pin instructions that survive compaction, /clear, and restarts. /pin saves a rule for this project and every prompt carries the pinned list as context Claude reads. 0
- pkg-guard 0.1.1 Hold npm, pnpm, yarn, pip, uv, and cargo installs of packages that don't exist, are brand new, or are barely downloaded, with the registry facts in the question. Catches hallucinated and typosquat packages before they land. 0
- red-green 0.1.1 Run the project's tests after any turn that edited files, print pass or fail under Claude's answer, and send the failure back to Claude with one /fix command. 0
- show-paths 0.1.0 Put the file path on every Read, Edit, Write, Glob, and Grep row in the transcript, so you never expand a row just to learn which file it touched. 0
- standup 0.1.0 Your day, written for you. Every turn is logged; /standup turns today's work across every session on the machine into a three-bullet update, or a Markdown file. 0
- style-cop 0.1.0 Enforce the style rules Claude keeps ignoring: banned words and phrases, a comment-density cap on added code, and files that must not gain comments. Rules live in .claude/style-cop.md and are both shown to Claude and enforced on edits. 0
- tripwire 0.1.0 Stop secrets leaving the machine. Holds an edit or command that writes an API key, a private key, or a credential literal, a command that reads a secret file and talks to the network, and a git commit whose staged changes contain a secret. Refuses by default. 0
- trust-but-verify 0.1.0 Check what Claude claims against what it ran. When an answer says the tests pass, the build is clean, or something was committed, a line under it says whether a matching command actually ran this turn and succeeded. 0
- undo-agent 0.1.1 Undo the file edits a subagent made. /rewind restores your own turns, but not a subagent's edits; this snapshots them and puts the files back with one command. 0
- usage-meter 1.0.0 Plan limits, time-to-limit pace, session cost, tokens, cache hit rate, context and model in the band above the prompt 0
- prompt-timestamp 1.0.0 Prefixes every prompt you type with the local date and time, visible to you and Claude. 0
- pomodoro 0.1.0 Pixel-art pomodoro timer in a side pane: /focus [minutes] 0
- agent-progress 0.2.0 Live progress bars for running subagents above the prompt 0
- cmd-guard 0.2.4 Blocks destructive shell commands (rm -rf /, force push, DROP TABLE...) 0
- model-router 0.2.0 Runs Explore subagents on haiku and general-purpose ones on sonnet unless a model was asked for 0
- control-tower 0.2.0 Control Tower: Flightdeck's live agent dashboard on top, savvy-progress's savvy-flow agents panel below, plus the progress band above the prompt 0
- painel-sessao 0.2.0 Session panel for Claude Code: the steps of the session with the current one marked, the decisions waiting for you, a queue of next prompts with auto-send, your last messages, notes, and the context window and plan limits. In Portuguese (Brazil) and English. 0
- mindgap 0.2.0 mod + skill Local org-roam-style knowledge graph (SQLite) with paper-ingest + loop skills and an MCP server 0
- pinboard 0.2.6 Keeps open decisions, the task list and links Claude creates in a sidebar pane, updated through its own tool 0
- tailpipe-board 0.1.0 A pane showing a tailpipe stream's recent lines, with a streams-picker button to switch which one is shown. 0
- code-wrapped 0.1.0 Your Claude Code Wrapped: activity heatmap, top files, coding personality and unlockable achievements. 0
- buildpane 0.1.9 Turns build, test and lint output from tsc, cargo, go, pytest, jest, gradle and more into a live pane of errors by file, and hands Claude the diagnostics instead of the raw log. 0
- sessions-panel 0.1.0 Панель живых сессий Claude Code и их статусов, по образцу Claude Control 0
- repo-radar 0.1.0 A live map of your codebase that lights up where Claude is working: reads glow cyan, edits amber, errors red, each subagent in its own colour. 0
- simpane 0.1.3 Puts the iOS Simulator beside your Claude Code session: a live screenshot, dark mode and text size switches, your app's own logs, and tools that let Claude see the screen for itself. 0
- watchtower 0.1.0 One line above the prompt showing what your guard mods are doing: the fence, pins, the breaker threshold, the test command and its last result, and every call refused this session. 0
- push-ups 0.3.0 Predicts how long Claude's turn will take and gives you push-ups to do while you wait, in a bar above the prompt. Local only: no model calls, no tokens. 0
- shared-repo-guard 0.1.4 For repos where several AI agents (or you and an agent) work in the same folder: stops secret values from leaving your .env, pushes to public remotes, and git commands that would wipe work this session did not write. 0
- session-memo 0.1.0 Per-session TODO and memo kept as Markdown, with a band above the prompt and a /memo pane 0
- session-tasks 0.3.1 A line above the prompt counting the background tasks running in every session, and a side panel listing them (shells, subagents, monitors, workflows) read from their transcripts, even in sessions marked Completed: /alltasks 0