All Claude Code modssruthik27/claude-foundry
insight-pane
Live pane of the decisions, root causes and gotchas worth knowing, fed into ~/learning notes
insight-pane reaches L2 (writes or runs) by its classified calls and passed claude plugin validate on Claude Code 2.1.303.
- Events hooked: 9
- API methods referenced: 20
- Access from classified calls: L2, writes or runs: runs processes, writes files, drives Claude, reads files, reads env vars, reads mod state, persists state, draws
- Calls in a namespace that is not in the Claude Code 2.1.302 core table: 1 (
$.lumen.markdown), full access unknown - Reads mod state: the scan does not record whose state, so this does not show that it reads another mod’s values
- Static scan, not a runtime test
Install hint
/plugin install insight-pane --marketplace sruthik27/claude-foundryFrom 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
L2 Writes or runsruns processes, writes files, drives Claude, reads files, reads env vars, reads mod state, persists state, draws, other: $.lumen.markdownValidation
Passed on Claude Code 2.1.303View the source on GitHub Back to the list
What the scan recorded
- Observed events
- classic hooks, every tool call, every prompt
- Hooks
session.start, classic.SessionStart, command.run {command=intel}, prompt.compose, turn.start, tool.call, prompt.submit, turn.complete, ui.render {component=AssistantMessage}, ui.render {component=Pane, requestId=insight-pane}- API calls
$.command.register, $.env.get, $.fs.exists, $.fs.read, $.fs.write, $.lumen.markdown, $.model.complete, $.process.run, $.session.id, $.state.get, $.state.set, $.store.delete, $.store.get, $.store.keys, $.store.set, $.ui.close, $.ui.open, $.ui.panes, $.ui.resolve, $.ui.status- Validation on 2.1.303
- Passed
- Scanned revision
5085c5908291- Marketplace passed
- claude-code-mods
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. What a mod can access and how the scan works.
More from sruthik27/claude-foundry
- asideRead-only side chat: /aside opens a pane beside the transcript where you ask about the session so far; answer…
- changes/changes: the session's edits grouped by concept, then files, then the exact code; point at lines and ask Cla…
- find-sess/find-sess <what you remember>: find a past session in this repo with a Haiku call, then resume it
- goal-meterLive overall-goal progress bar above the prompt, from the task tools plus Claude's per-turn goal estimate
- live-progressLive progress bands above the prompt for long-running work Claude starts: tests, builds, scripts, logs
- lumenColourful, themeable rendering for Claude Code replies, with animated diagrams, timelines, state machines and…
- mcp-controlLets Claude see every configured MCP server, ask you (one click) to enable one that is off here, and reconnec…
- self-drive/self-drive: hand Claude a task and walk away; it decides alone, logs every call it would have asked you, hol…
- session-namerGives each session a short findable name on exit, and re-checks it on later exits
- skills/skills: per-prompt skill suggestions, what Claude actually loaded, and one-key use of a suggested skill
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/sruthik27--claude-foundry--insight-pane/)
[](https://mods.aidojo.si/mods/sruthik27--claude-foundry--insight-pane/)