{
  "batch": "read1-146",
  "plugins": [
    {
      "pr": 0,
      "name": "done-bell",
      "does": "Notifies the user when a Hermes turn ends or waits for approval, with a status pane and command.",
      "useful": 3,
      "reliable": 4,
      "polish": 4,
      "creative": 2,
      "beyond": 4,
      "total": 21,
      "best": "It registers lifecycle and approval hooks, persists local state, and includes focused unit tests and a Desktop pane.",
      "worst": "Its notification-only benefit is narrow and its documented Desktop pane setup still needs a manual copy step.",
      "standout": false,
      "blocked": null
    },
    {
      "pr": 0,
      "name": "homeassistant",
      "does": "Connects Hermes to Home Assistant events, notifications, and device query/control tools.",
      "useful": 5,
      "reliable": 5,
      "polish": 5,
      "creative": 3,
      "beyond": 5,
      "total": 28,
      "best": "It is a complete, tested smart-home platform integration with entity allow/deny controls and service-call safeguards.",
      "worst": "It necessarily depends on a high-privilege Home Assistant token and instance-specific configuration.",
      "standout": false,
      "blocked": null
    },
    {
      "pr": 150351,
      "name": "blazephoenix",
      "does": "Gets DEX swap quotes through the user's RPC and locally checks unsigned router calldata before signing.",
      "useful": 3,
      "reliable": 4,
      "polish": 4,
      "creative": 4,
      "beyond": 4,
      "total": 23,
      "best": "It never signs or handles keys and cross-checks its hosted decode and calldata against a user-configured RPC response.",
      "worst": "Quotes still rely on BlazePhoenix's hosted prepare/decode service and an independently configured RPC endpoint.",
      "standout": false,
      "blocked": null
    },
    {
      "pr": 153792,
      "name": "smriti",
      "does": "Provides local MCP personal memory with scoped, dated facts, history, retrieval, and source evidence.",
      "useful": 5,
      "reliable": 5,
      "polish": 5,
      "creative": 4,
      "beyond": 5,
      "total": 29,
      "best": "Its local SQLite MCP server preserves corrections and temporal evidence while validating inputs and containing database access.",
      "worst": "Memory capture remains explicit tool use, so it does not automatically retain a conversation the agent never sends to it.",
      "standout": true,
      "blocked": null
    },
    {
      "pr": 153758,
      "name": "hermes-cobrowse",
      "does": "Runs multi-window Playwright browsing in a live local canvas where a person can take over and resume the agent.",
      "useful": 4,
      "reliable": 2,
      "polish": 5,
      "creative": 4,
      "beyond": 5,
      "total": 25,
      "best": "It implements a polished, real multi-session browser canvas with CDP frames, telemetry, and a tested human 2FA handoff.",
      "worst": "Its agent tools still expose unrestricted browser clicking and page JavaScript, with no code-enforced approval or handoff gate for sensitive actions.",
      "standout": false,
      "blocked": null
    },
    {
      "pr": 153938,
      "name": "syrinx",
      "does": "Uses Hermes hooks to defer agent questions, hold outward actions during focus time, and return a counted catch-up.",
      "useful": 4,
      "reliable": 5,
      "polish": 5,
      "creative": 5,
      "beyond": 5,
      "total": 29,
      "best": "It turns runtime hooks into a carefully tested attention-control layer with safe outward-action holds, receipts, Desktop UI, and pet feedback.",
      "worst": "Its outward-action classifier is necessarily a fixed heuristic, so unrecognized tools or command forms can evade a hold.",
      "standout": true,
      "blocked": null
    },
    {
      "pr": 151102,
      "name": "crash-test",
      "does": "Injects bounded one-turn tool failures and rates how an agent retries, works around them, or reports uncertainty.",
      "useful": 4,
      "reliable": 4,
      "polish": 4,
      "creative": 5,
      "beyond": 5,
      "total": 27,
      "best": "Its per-session, one-turn harness blocks loud failures before execution and restricts silent corruption to eligible reads, backed by full-hook tests.",
      "worst": "The final rating infers honesty from transparent reply-pattern heuristics, so unusual but honest wording can be scored incorrectly.",
      "standout": false,
      "blocked": null
    },
    {
      "pr": 150189,
      "name": "sequenzy",
      "does": "Connects Hermes to Sequenzy's hosted email-marketing MCP service and bundles operating instructions.",
      "useful": 3,
      "reliable": 2,
      "polish": 3,
      "creative": 2,
      "beyond": 3,
      "total": 16,
      "best": "It uses OAuth, labels the remote server untrusted, and documents that writes and sends need approval.",
      "worst": "The pinned package contains no implementation or tests; it downloads an npx bridge and delegates its changing tool set to a hosted service outside the commit.",
      "standout": false,
      "blocked": null
    },
    {
      "pr": 149226,
      "name": "zambo-receipts",
      "does": "Journals Hermes tool calls and creates public, verifiable Zambo session receipts.",
      "useful": 3,
      "reliable": 3,
      "polish": 4,
      "creative": 4,
      "beyond": 5,
      "total": 24,
      "best": "It uses lifecycle hooks, hash-only journaling by default, bounded durable retry buffering, and tests its receipt lifecycle.",
      "worst": "Automatic journaling and wrapping send session metadata to an external service and publish a receipt by default, making its value dependent on a third party and careful user configuration.",
      "standout": false,
      "blocked": null
    },
    {
      "pr": 153520,
      "name": "ghostrun",
      "does": "Builds a GPU-assisted pipeline for observing NES games, training a player, isolating a reference oracle, and validating editable recreations.",
      "useful": 2,
      "reliable": 4,
      "polish": 5,
      "creative": 5,
      "beyond": 5,
      "total": 26,
      "best": "It is an unusually complete plugin runtime with durable stages, reference/builder isolation, a black-box oracle, a CUDA training pipeline, and extensive adversarial tests.",
      "worst": "It is an early-preview workflow for a very narrow audience that requires a user-supplied ROM, Linux, NVIDIA CUDA, and substantial local setup.",
      "standout": false,
      "blocked": null
    },
    {
      "pr": 154056,
      "name": "chatgpt-style",
      "does": "Adds a ChatGPT/Codex-inspired light and dark visual theme to Hermes Desktop.",
      "useful": 3,
      "reliable": 2,
      "polish": 4,
      "creative": 2,
      "beyond": 4,
      "total": 19,
      "best": "It is a substantial, well-documented theme that uses the Desktop theme API without network, storage, or agent-side privileges.",
      "worst": "It has no tests and relies on many Desktop data-slot and class selectors that can silently break as the host UI changes.",
      "standout": false,
      "blocked": null
    }
  ]
}