Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By mistakeknot
Agent-as-operator runtime diagnostics — teaches agents to observe and control running applications via diagnostic HTTP servers and CLI tools.
npx claudepluginhub mistakeknot/interagency-marketplace --plugin interhelmUse when verifying critical user journeys in a running application without screenshots — queries structured /diag/ui/state endpoints for semantic UI state instead of visual inspection.
Use when evolving a basic diagnostic server scaffold into a production-grade operator toolkit. Guides 6 maturation levels (domain health → smoke tests → assert language → CLI formatting → diff engine → REPL+watch) with verification gates.
Use when verifying a running native app works after code changes, you cannot use browser DevTools, or need to check runtime state without screenshots. Guides scaffolding a diagnostic HTTP server with Health, Diff, Assert, and Smoke Test patterns for Tauri/Electron apps.
Use when designing end-to-end verification for a running application — teaches the executable contract pattern where smoke tests serve as the agreement between diagnostic server and CLI client.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Use this agent when monitoring system health, optimizing performance, managing scaling, or ensuring infrastructure reliability. This agent excels at keeping studio applications running smoothly while preparing for growth and preventing disasters. Examples:\n\n<example>\nContext: App experiencing slow performance
Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.
Observability engineering agents providing expertise in tracing, monitoring, and logging
Expert guidance and automation for mobile app observability: crash reporting, performance monitoring, session replay, and instrumentation for iOS, Android, React Native, and Flutter.
Real-time observability dashboard for Claude Code agents
Lightrun runtime investigation skills for deterministic, evidence-first debugging.
[DEPRECATED — use intervoice] Analyze your writing style and adapt Claude's output to sound like you. Replaced by intervoice, which reads one global multi-register profile instead of per-project glob-routed files.
Recursive AGENTS.md generator with integrated Oracle critique, CLAUDE.md harmonization, incremental updates, diff previews, and smart monorepo scoping. Cross-AI compatible.
Self-improving agent rig: codifies product and engineering discipline into composable workflows from brainstorm to ship. Compounds knowledge, generates domain agents, monitors its own docs, and surfaces conservative update drift. Orchestrates Claude, Codex, and Oracle through 6 agents, 52 commands, 19 skills, 0 MCP servers. Factory substrate: CXDB turn DAG, scenario bank with satisfaction scoring, evidence pipeline, agent capability policies. Companions: interspect, interphase, interline, interflux, interpath, interwatch, interslack, interform, intercraft, interdev, interpeer, intertest.
Token-efficient code reconnaissance for LLMs. Autonomous skills save 48-85% tokens via diff-context, semantic search, structural patterns, and symbol analysis. Includes MCP server for direct tool integration.
Token efficiency benchmarking, session analytics, and API-equivalent cost analysis for agent workflows
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Agent-as-operator runtime diagnostics for the Interverse plugin ecosystem.
Teaches agents to observe and control running applications via diagnostic HTTP servers and CLI tools. Instead of taking screenshots, agents query structured JSON endpoints for runtime state — including UI state.
claude plugins install interhelm
| Pattern | What It Does |
|---|---|
| Health | Structured pass/fail per subsystem |
| Diff | Snapshot state, take action, show what changed |
| Assert | Scriptable verification expressions |
| Smoke Test | End-to-end flow verification (executable contract) |
The killer feature: /diag/ui/state returns semantic JSON describing what's on screen — active view, panel states, selections, form values. Agents verify CUJs without screenshots at near-zero token cost.
The skills guide agents to scaffold a diagnostic server and CLI for your project:
runtime-diagnostics — Scaffolds the full diagnostic HTTP server with all patternssmoke-test-design — Designs executable contracts between server and clientcuj-verification — Validates user journeys via structured state queriestemplates/rust-hyper/ — Rust diagnostic server skeleton (hyper)templates/cli/ — Thin CLI client with formatters, watch mode, REPLinterhelm/
├── .claude-plugin/plugin.json # Plugin manifest (3 skills, 1 agent)
├── skills/
│ ├── runtime-diagnostics/ # Main skill — 4 patterns + UI state
│ ├── smoke-test-design/ # Executable contract pattern
│ └── cuj-verification/ # Screenshot-free CUJ validation
├── agents/review/
│ └── runtime-reviewer.md # Operational review agent
├── hooks/
│ ├── hooks.json # 3 PostToolUse hooks
│ ├── browser-on-native.sh # Detect screenshot use on native apps
│ ├── auto-health-check.sh # Health check after Rust changes
│ └── cuj-reminder.sh # CUJ verification reminder
├── templates/
│ ├── rust-hyper/ # Diagnostic server skeleton
│ └── cli/ # CLI client skeleton
├── scripts/bump-version.sh
├── tests/structural/ # Plugin structure validation
├── CLAUDE.md, AGENTS.md, PHILOSOPHY.md, LICENSE
└── README.md
See PHILOSOPHY.md for design bets and tradeoffs.
MIT