agent-dock
by Koren Kazoom · ★ 0 · updated 4 days ago
Agents side panel with run, pause, stop and open-in-tab controls, plus a context window bar with a Compact button
Install
git clone https://github.com/korenka/claude-harnessclaude --plugin-dir ./claude-harness/mods/agent-dockThen run /reload-plugins or start a new session. Requires Claude Code 2.1.287+.
What it hooks into
From an automated scan with claude plugin validate, not a security review. Mods run with your permissions; read the code before installing.
- Events
session.startsession.compactcommand.runui.renderagent.offerturn.completesession.append- API calls
$.agent.list$.agent.spawn$.clock.every$.command.register$.command.run$.env.get$.fs.exists$.fs.list$.fs.read$.session.compact$.session.messages$.session.root$.session.send$.session.usage$.state.get$.state.set$.tool.call$.ui.close$.ui.open$.ui.panes$.ui.resolve$.ui.toast- Draws
AbovePromptPane- Can see
compaction- Reach
- level 2 of 3 other: $.state.getother: $.state.setdrives Claudereads filesreads env varsreads the transcriptdraws
Origin
- How it got here
- Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of ).
- Repository
- github.com/korenka/claude-harness
- Path in repo
mods/agent-dock- Source commit
22238e6the exact code the scan read- Author
- Koren Kazoom @korenka
- License
- MIT
- First published
- Last pushed
- First listed here
Name and description come from the mod's own manifest. We link to the code; we don't host it, and it stays under its author's license.
More from korenka/claude-harness
blind-spots
korenka/claude-harness
Adds a Blind Spots button above the prompt that asks Claude to list the engineering blind spots in the current plan or design
diagram
korenka/claude-harness
Adds a Diagram button that draws the flow or architecture from Claude's latest response in its own pane tab, saved as SVG and draw.io
help-offers
korenka/claude-harness
Turns the 'How I can help' list at the end of an answer into buttons that start a subagent for each offer
rephrase
korenka/claude-harness
Adds a Rephrase button that rewrites the draft in the prompt box with a small model, so the LLM gets a clearer, structured prompt. Undo restores the original
tldr
korenka/claude-harness
Adds a TLDR button that summarizes Claude's latest response in a side pane