After each commit the model makes, names the env variables its added lines read that .env.example lacks, with the file and line of each.
✳︎ env-sync
└─ Make every conversation easier
Claude Code mods, plugins, skills, hooks, status lines and MCP servers. Browse community builds with original sources and L0–L3 permission levels.
1,550 projectsAfter each commit the model makes, names the env variables its added lines read that .env.example lacks, with the file and line of each.
A Claude Code function-hook plugin that adds a /worktrees pane listing each git worktree with branch, uncommitted changes, ahead/behind and PR state, and can remove clean worktrees whose PR is merged or closed.
A band above the prompt with how many tool calls failed this session (an error or a deny) and which tool failed last. Red from the first failure.
BazaarLink is an OpenAI-compatible AI API gateway: one key for 140+ AI models, pay as you go, with budget limits.
bazaarlink.aiVisit sponsor ↗A Claude Code plugin that replaces /recap with a structured recap (Goal / Done / Open / Next) rendered as a card with session name, model and context-use bar.
Claude Code plugin that collapses tool calls into one-line rows, hides tool result blocks, and draws inline PNG thumbnails under image-related rows.
Spinlings is a Claude Code mod: a creature card game that battles above your prompt while Claude works, with hooks documented and installable via the plugin marketplace.
Track what your AI coding tools cost
syrtis.nyanako.comVisit sponsor ↗A Claude Code plugin that hooks Edit, Write and NotebookEdit tool calls, counting successful edits per file and turn; at the third edit it warns the user and at the fifth it sends the model a note to stop editing, re-read the code path and state the root cause. Counts reset each turn and are tracked separately for the main loop and subagents.
A Baselane Claude Code guard that asks before a command prints environment variables, echoes a sensitive variable, or sends local data to a remote host.
A Claude Code plugin that rates each prompt's difficulty with a small model and runs that turn and its subagents at the matching effort level, within user-allowed limits, on models whose prompt cache survives effort changes.