Guards

My unofficial fan mod that makes Claude Code cute. Claude-sama, a small kami of words, reads along above your prompt, keeps an offering box for your context window and draws you one omen a day. Terminal and desktop. Not affiliated with Anthropic.

Consultation and prompt engine for Claude Mods. The module is the core; [probe. ] tables in probes.toml are the consultants and [prompt. ] tables author a system-prompt section, a tool description or a command description. The only carrier is the mod: a CLAUDE_*_CARRIER handle set to mod or left empty/unset arms the probe here; any other value loudly refuses the calls this probe acts on (the...

Makes every response the service filter stopped visible at once and adds a rule: report it, do not drop work silently.

Multi-line status HUD above the prompt over data families (hooks/data/*.ts pure collectors, one core subscription per event), with the /statusline-mod pill panel: live preview, six tabs (layout, elements, per-element settings, view axes, themes, number formats). Based on konsta95/ClaudeCodeMods statusline 0.3.2 (MIT, c49ad4a).

Optional Claude Code 2.1.274 and 2.1.280 function hooks for Signet-eval policy and output redaction

Shows the model's real output speed, token and prompt-cache stats in a docked sidebar beside the transcript.

Ricky, a pixel-art cat companion for Claude Code: an animated night-sky pane with a task / subagent / activity / files board, a cat in the band above the prompt, and a purple-gold spinner

Write to Claude Code in your own language while Claude works in English: prompts are translated to English, and each reply gets a streamed translation underneath.

Game and HTML panels backed by the headless Katzensteg WM. Needs CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1.

A little pixel cat that wanders above the Claude Code prompt, watches your usage limits and announces when work finishes

Claude çalışırken istemin üstünde piksel Minecraft sahnesi: Clawd kazar, inşa eder, TNT patlatır

Draws the agentic-workflows engine's gates in the band above the prompt — rows a click puts in the prompt and a second click sends — instead of a menu the model has to reproduce.

Jev Gate in one plugin: the orchestration gate, the extractive compactor, the Vitest log folder, the Jev effort and model router and the jev_evidence tool. Every part is on by default; each has its own on/off option.

Folds runs of identical consecutive lines in a passing Vitest log the host saved to a file, so the model reads the whole run with exact counts instead of a 2 KB preview; on by default.

Records which real checks ran and which files changed after them; status line, /evidence, and an evidence tool Claude reads before claiming tested.

Routes decisions to TypeSafe's Jev model: ranks installed skills for each prompt, and answers the agent's own this-or-that questions when confident.

Keeps secrets, email addresses and IP addresses out of the session transcript: swaps each one for a stable placeholder on the way in, and puts the real value back on the way into a tool call

Pins the Vercel deploy queue of the linked project under the prompt: every deploy queued, building or just finished, with its phase and elapsed time

Mission control for your subagents: every spawned agent becomes a live, animated card above the prompt, with its phase, effort, tools, cost and a timeline you can follow

A usage band above the prompt — context, 5-hour limit, weekly limit, cache hit rate — with Clawd, an animated pixel pet. For the Code tab of Claude Desktop.

See your Claude Code session at a glance: context left, cost and today's spend, rate limits, git diff and PR status, right above the prompt. Set /budget limits and get a toast before you go over. Open the detail panel for context breakdown, turns, cache hit rate and top tools. Works in the CLI and the desktop Code tab.

5dive telemetry producer, seat panel, command surface and tool-call policy guard for Claude Code function hooks (early access). Publishes turn and session boundaries and the account's usage reading from inside the harness process to a per-seat JSONL sink, so the heartbeat, the pacing floor and the self-update's pending-restart sweep can read a first-class signal instead of inferring idle/busy...

29 bundled skills, 10 specialist agents, smart worktree hooks, statusline, and MCP server stubs — plan, implement, review, debug, multi-agent setup, and audit code from one plugin.

A side pane for Claude Code that lists the subagents a session runs, what each is doing and what it costs in tokens, with each one's conversation a click away.