human-gate 0.1.0
Holds irreversible tool calls (deploys, publishes, protected pushes, money, outbound messages, destructive SQL) for a person; lets read-only calls through.
Install
/plugin marketplace add 01000001-01001110/claude-mods /plugin install human-gate@claude-mods
Run both lines inside Claude Code.
Hooks into
- Status line
- Tool calls
- Slash commands
Also in 01000001-01001110/claude-mods
- screen-share 0.1.0 Screen share mode: masks keys, tokens, env values, user paths, emails, phone numbers, money and names on screen while you present or stream, with an ON AIR mark 0
- atlas 0.1.0 Map the repo you are in: what it needs to run and what is missing (gaps with file:line first), then its modules, how they depend, entry points, hot spots and cycles. /atlas opens the pane; export to Markdown with mermaid and HTML. 0
- brain-dump 0.1.0 Catches a long or rambling prompt, asks a few clarifying questions, and puts a structured rewrite (Task / Why / Guardrails / Done looks like) in the prompt box for you to review and send 0
- chat-inventory 0.2.0 An "In this chat" pane like Cowork's side panel: goal, to-do progress, connectors and skills used, files made, changed or read, and tool counts, each section foldable (/inventory) 0
- context-meter 0.1.1 Context usage meter above the prompt: raw and usable fill with the autocompact mark, turns-to-autocompact forecast, prompt-cache countdown and miss detection, files changed on disk since read, compactions, and a FRESH/AGING/STALE/COLD verdict. 0
- effort-picker 0.1.0 Reads the prompt as you type and suggests a model and effort above it, with the reason and a re-cache marker; Use applies it to the next turn only 0
- handoff 0.1.0 Moves the work to a fresh chat: offers a handoff past a token threshold or when the prompt cache goes cold, writes it through a fork of the session, saves it under ~/.claude/handoffs, and clears only when you confirm, leaving the handoff in the prompt box. 0
- switchboard 0.2.0 /switchboard (and /mods where free) opens one pane to switch mods on or off at their next load and to block their new panes now, with an honest card per mod: now, next load, panes 0
- agent-roster 0.1.0 Flight deck pane: main loop, every subagent as a card with avatar, clock, task, tokens and effort, plus a permission gate, turn receipt and event log 0
- burn 0.1.0 Session and weekly usage gauges under the prompt, cost and burn rate, a runs-out-at forecast and usage history; nudges you to spend the weekly limit before it resets, or to ease off when burning too fast. 0
More status line mods
- jev-auto-mode 0.1.1 A permission layer driven by a JSON policy: allow, ask or deny every tool call (Bash, edits, web, MCP, subagents, skills), every slash command or skill you type, and every skill preloaded into a subagent. Rules decide first (deny > ask > allow, compound Bash commands split); what no rule covers c... 33.4k
- cache-clock 0.1.1 A prompt-cache line under your status line, from Claude Code's own cache figures: time left while warm, hit rate and misses, and how many tokens the next message re-caches once cold. /cache-clock setup adds it. 473
- secrets-veil 0.0.11 Masks secret values in tool results before the model reads them: named vendor variables, value-shape patterns, and high-entropy tokens. No reveal path. 302
- lemo-meter 0.2.0 用量横条:输入框上方显示上下文、5 小时额度、花费和 git 分支;状态栏显示消息编号(已有自己的状态栏时默认关闭);点「检查」才联网查新版本 / Usage meter: context, 5-hour quota, cost and git branch above the prompt; a status line with the message number (off by default if you have your own); checks for updates online only when you press Check 71
- glowup 1.2.0 mod + skill A glow-up for Claude Code: a cockpit pane for changes, subagents and context, an activity band, and shareable themes. 41