All Claude Code modsbqnhat/claude-local-plugins
session-hub
One Mod status pane for Claude Code Desktop with an icon rail: Progress (live plan bars with step times and history, forked from zycck/claude-mods plan-progress), Next steps (up to three suggested next prompts; a click puts one in the composer), Skills & agents (the skills and agents called this session, each tagged personal, project, plugin or built-in, plus the rule and CLAUDE.md files loaded) and Cache (cache reads, writes and hit rate per turn, and what the cache saved). One footer entry opens the pane; the terminal keeps the progress band and the next-steps band
The scan could not record a complete footprint for session-hub, so its access is unknown; it passed claude plugin validate on Claude Code 2.1.302.
- Access: unknown, the footprint is incomplete
- Static scan, not a runtime test
Install hint
/plugin install session-hub --marketplace bqnhat/claude-local-pluginsFrom the repository's own marketplace. Confirm the plugin name in the repository's README before installing. Mods need Claude Code 2.1.287 or later.
Access
Unknown accessThe footprint is unavailable or incomplete.Validation
Passed on Claude Code 2.1.302View the source on GitHub Back to the list
What the scan recorded
- Footprint
- Unavailable or incomplete. Recorded events and calls below may omit access.
- Observed events
- every prompt, compaction, every tool call, mcp__session-hub__plan_progress calls, AskUserQuestion calls, ExitPlanMode calls, subagent spawns, every skill, classic hooks, Skill calls, Agent calls
- Hooks
prompt.submit, session.compact, session.end, tool.call, session.attach, session.detach, tool.call {tool=mcp__session-hub__plan_progress}, tool.call {tool=AskUserQuestion}, tool.call {tool=ExitPlanMode}, command.run {command=progress}, command.run {command=progress-demo}, command.run {command=progress-clear}, command.run {command=progress-sounds}, agent.spawn, tool.check, turn.step, command.run, skill.prompt, prompt.attachment, classic.InstructionsLoaded, session.end {reason=clear|resume}, agent.offer, tool.call {tool=Skill}, tool.call {tool=Agent}, session.start, turn.start, turn.complete, ui.render {component=AbovePrompt}, command.run {command=session}, ui.close, ui.render {component=SessionMode}, ui.render {component=Pane, requestId=session-hub}- API calls
$.agent.list, $.audio.play, $.clock.after, $.clock.every, $.clock.now, $.command.list, $.command.register, $.env.get, $.model.complete, $.model.fork, $.process.run, $.prompt.fill, $.prompt.submit, $.prompt.suggest, $.session.cwd, $.session.id, $.session.messages, $.session.surfaces, $.session.usage, $.state.get, $.state.set, $.store.get, $.store.set, $.tool.register, $.ui.close, $.ui.invalidate, $.ui.log- Validation on 2.1.302
- Passed
- Scanned revision
d2453277d6f9- Marketplace passed
- nhat-local
These are the hooks and API calls reported by claude plugin validate. Access levels describe the widest reach of those calls and are not safety ratings. Validation is a static check, not a runtime test, and a passing result does not prove that a mod works or is safe. How the scan works.
More from bqnhat/claude-local-plugins
- cache-timerShows how long the prompt cache stays warm, as a dim Cache mm:ss countdown in the footer of Claude Code Deskt…
- next-steps-desktopAfter each turn, suggests up to three next prompts: above the input in the terminal, behind a 💡 chip in the…
- plan-progressLive plan progress bars with stages, steps, step times and soft sounds for decision, error and done. Local fo…
Badge for your README
Authors can show the latest scan result in their README. Each badge links to this page.
[](https://mods.aidojo.si/mods/bqnhat--claude-local-plugins--session-hub/)
[](https://mods.aidojo.si/mods/bqnhat--claude-local-plugins--session-hub/)