Claude Code mod
loose-ends
A live checklist above the prompt of the conversation's loose ends: questions left unanswered, points made in passing, caveats and deferred work it moved past, kept up to date by a small model after each turn. Needs function hooks (early access) and an interactive terminal.
Install
/plugin marketplace add fernandomoraes/loose-ends
/plugin install loose-ends@loose-endsMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L2Writes or runs: drives Claude, reads the transcript, persists state, draws
- Draws in
AbovePrompt- Hooks
session.startturn.startturn.completecommand.runui.render
From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.
How Claude Code mods work
- A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
- It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
- Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
- Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Details
- Repository
- fernandomoraes/loose-ends
- Folder
.- Marketplace
loose-ends- Author
- Fernando Moraes
- License
- MIT
- Last updated
- 22 September 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is loose-ends?
A live checklist above the prompt of the conversation's loose ends: questions left unanswered, points made in passing, caveats and deferred work it moved past, kept up to date by a small model after each turn. Needs function hooks (early access) and an interactive terminal. It is a mod for Claude Code, from fernandomoraes/loose-ends on GitHub.
What can the loose-ends mod access?
Its widest reach is "writes or runs" (drives Claude, reads the transcript, persists state, draws). It draws in AbovePrompt. Like any mod, it runs with your permissions.
How do I install loose-ends?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add fernandomoraes/loose-ends and then /plugin install loose-ends@loose-ends.
More pane & dashboard mods
loop-graph
ziedgithub/claude-code-mods
Live graph of any project's agent loop in a side pane: the step at work, the path the run takes with its labelled arcs, each agent sent with its time and share of context, and the commands running. Comes with /loop-graph:setup, which maps a project's loop
luff-crew-monitor
tanwar-harsh/luff-crew-monitor
Live crew panel inside Claude: every subagent with model, effort, steps, context, estimated cost and time, plus a job bar above the prompt and your 5-hour and weekly plan limits. /agents-info toggles it; /agents-web opens an optional browser view.
looked-at
ozdeger/claude-looked-at-mod
See every image and file the agent looked at: screenshots, renders and file reads in a pane of the Claude desktop app, built from session output only
markdown-pane
JorgeRomero123/claude-markdown-pane
Opens Markdown files rendered in a side pane: from a button on the row that wrote them, when asked in plain words, or by itself for a new report
logpane
benlrice/logpane
A pane that tails the files your Bash calls write to, so you can watch long-running output without a second terminal.
market-watch
rajib2k5/claude-market-watch
Stock ticker in the status line, /quote pane, price alerts, a market-context band, and a quote tool the model can call.
Browse the most popular Claude Code mods, all pane & dashboard mods, or the skills and MCP server directories.