Claude Code and Codex plugins their authors filed under "productivity". All categories.
Nothing is written before a copy exists, nothing is read before you have seen the list, and no answer ends without saying what nobody checked. Plus three ready readings of a document: where the catch is, what the plan is missing, what here is fact.
A second opinion from a DIFFERENT company's AI, and an honest account of where the two disagreed - because two AIs agreeing is not proof. Works through a free browser chat when no second program is installed.
Leave the computer working and take the phone, without finding out in town that it never started: the seven silent reasons an evening away fails, checked before you leave.
Persistent semantic memory for saving facts, patterns, and decisions across sessions
Google Workspace CLI — Drive, Gmail, Calendar, Sheets, Docs, Tasks via gws
Generate images, photos, icons, diagrams, thumbnails, banners, and visual assets
Groundwork is a Codex-native workflow layer for evidence-first software R&D: clarify scope, ground decisions in code/runtime evidence, choose the lightest path, and ship reviewable artifacts.
No description.
Codex plugin for the live HIVE-MIND MCP bridge
No description.
No description.
Check sjskills CLI and configured skill status at startup without assigning agent work.
my everything-claude-code
Fabric port of Chisels and Bits for Minecraft 26.2. Carve blocks into 16³ voxel bits, place them, and sculpt detailed builds.
No description.
Free internet radio, and any song through hum, above the prompt. Steps down when Claude asks you a question.
Interview you and help you build your dream AI persona faster.
Mod: an Enhance button above the prompt box (or /enhance <draft>) opens a popover that rewrites your draft as a Precise prompt or an Expert agents prompt (picks the right experts, e.g. senior reviewer, architect + PM, and has Claude run one subagent each). Uses session context; you review before sending. Opt-in, separate from growmax-skills.
Tracks OpenAI Codex CLI runs started from Bash: /codex pane and status-line entry with session id, elapsed time, status and token usage.
Draws done/total from the project TASKS.md and the next open item in a band above the prompt.
Text-to-speech offline em portugues do Brasil para Claude Code. Hook Stop sintetiza audio do output do agente via Kokoro local (neural, voz feminina pf_dora) com pre-processamento que strippa codigo, paths e markdown antes de virar fala. Sem API key, sem limite (apos setup inicial). Windows 11 + PowerShell 7. Changelog completo em CHANGELOG.md no repo.
Live progress of every long-running job above the Claude Code prompt: bars, speed, ETA, stall and crash detection
Hands back the conversation itself in place of a compaction summary, less the tool calls and results a System One decision model judges no longer needed. The model can be TypeSafe Jev, Cloudflare Clef, Codiv OpenJev, Perplexity pplx-decider, OpenAI GPT-6 Luna, or Jev through OpenRouter, decisions-api.dev or decisionapi.net.
Air-traffic control for subagents: a live pane listing every agent, what each one is doing now, and controls to message or stop one. Open it with /atc.
Enforces the forge phase gate: shows whether the current phase's Verifiable gate is green on exactly the files you have, and sends back a forge stage whose FORGE_RESULT claims "gate":"green" when it isn't. /gate runs it.
Flag a project for prototype mode: no git worktrees, Claude edits the current checkout directly. Works for background jobs too.
Open a terminal split, tab or window in the session's worktree or any agent's worktree: /term, or the buttons above the prompt
Human-in-the-loop skills: get grilled on a decision, turn a blocked question into a questionnaire, mine yourself for writing fragments and shape them into an article, and chart work too big for one session as a map on Linear. Ported from mattpocock/skills.
General-purpose tools: conversation-history search, web-scraper, field-notes, and wizard scripts that walk a human through manual setup.
No description.