{"batch": "read1-147", "plugins": [{"pr": 0, "name": "done-bell", "does": "Fires a local desktop/OS notification and status chip when a Hermes agent turn ends or needs approval, tracked via session/approval hooks.", "useful": 3, "reliable": 4, "polish": 3, "creative": 2, "beyond": 4, "total": 20, "best": "Clean hook-based integration (on_session_end, pre/post_approval, agent_loop_stopped) plus a real desktop UI chip, with every handler defensively wrapped so it never raises.", "worst": "The idea itself (notify when agent is done) is a common utility pattern, and the catalog.yaml still has a placeholder 'REPLACE_WITH_40_CHAR_COMMIT' sha, suggesting the submission wasn't fully finalized.", "standout": false, "blocked": null}, {"pr": 0, "name": "homeassistant", "does": "Official Nous Research plugin that adds a Home Assistant gateway platform (WebSocket state feed) plus four tools to list/get/call Home Assistant entities and services, letting the agent control real smart-home devices.", "useful": 5, "reliable": 4, "polish": 5, "creative": 3, "beyond": 5, "total": 27, "best": "Deep, security-conscious integration: a new gateway platform with WS reconnect/heartbeat, SSRF-safe regex validation, a domain blocklist for dangerous HA services, secrets read exclusively via Hermes's own secret-scope API, and 176 test functions across 6 files.", "worst": "ha_call_service can directly act on real physical devices (locks, climate, etc.) with no plugin-level human-approval step of its own; it relies entirely on Hermes core's own approval system plus its own blocklist, a risk the README is transparent about but doesn't eliminate.", "standout": true, "blocked": null}, {"pr": 149719, "name": "agentic-kingdoms", "does": "A thin bundle (MCP server pointer plus a skill document) that lets the agent play a third-party-hosted browser MMO via a hosted MCP server, with no plugin-authored code at all.", "useful": 2, "reliable": 2, "polish": 3, "creative": 3, "beyond": 1, "total": 12, "best": "The underlying game concept (agents playing a persistent MMO, 'Humans vs AI war') is a creative idea, and the README is transparent about its limited scope and risks.", "worst": "By its own admission ('There is no executable code and nothing that downloads or updates itself') this is just an MCP passthrough plus a skill file \u2014 all logic lives on a third party's server, so a skill/MCP config alone could reproduce it, and it runs game actions including attacks on other players without per-action approval by default.", "standout": false, "blocked": null}, {"pr": 152277, "name": "plan-usage", "does": "A Hermes Desktop status-bar/dashboard plugin that aggregates plan-usage percentages across the user's Claude/ChatGPT credential pool, Nous Portal credits, and optional Anthropic/OpenAI org API spend.", "useful": 4, "reliable": 5, "polish": 4, "creative": 3, "beyond": 4, "total": 24, "best": "Unusually rigorous reliability: secrets read exclusively through Hermes's secret-scope API (never os.environ/.env), enforced by both a runtime test and a static AST test that bans raw env/token access, plus a redirect-refusal test proving admin-key headers can't leak via HTTP redirects.", "worst": "The underlying idea (a usage dashboard) is not novel \u2014 the README itself lists six competing catalog plugins it differentiates against \u2014 and it ships no screenshots despite a full desktop UI.", "standout": false, "blocked": null}, {"pr": 149968, "name": "lahja", "does": "A fully local, dialect-aware Arabic speech-to-text provider for Hermes built on whisper.cpp, with hallucination filtering, a user-teachable correction system, and automatic routing of non-Arabic audio to a secondary model.", "useful": 4, "reliable": 5, "polish": 5, "creative": 5, "beyond": 5, "total": 29, "best": "Genuinely novel, narrow-domain engineering: registers a real TranscriptionProvider subclass, runs subprocesses with a minimal explicit environment so API keys can't leak to whisper-cli/ffmpeg, SHA-256-verifies downloaded models, and is self-critical in its own benchmark (admits it is worse than stock Whisper on some dialects).", "worst": "A minor documentation inconsistency: the README claims '99 tests' while a plain count of test functions in the repo's test files comes to about 69 (likely explained by parametrized cases, but not verified).", "standout": true, "blocked": null}, {"pr": 153580, "name": "eta", "does": "A deterministic statistical ETA calculator for agent/kanban/cron work that tracks run history in a local SQLite file and computes likely/worst-case time ranges with percentile and queueing math.", "useful": 3, "reliable": 5, "polish": 4, "creative": 3, "beyond": 4, "total": 23, "best": "No network calls, shell commands, or credentials at all; opens Hermes's own kanban/cron/session databases strictly read-only (mode=ro, query_only pragma), and the README is candid about its own limitations and past bugs found via backtesting.", "worst": "The underlying feature category (time estimation for work queues) is fairly common, and there is no visual/UI polish (no screenshots, no desktop UI) despite thorough text documentation.", "standout": false, "blocked": null}, {"pr": 150059, "name": "starlearner-nexus", "does": "Fetches a user's starred GitHub repositories, keeps an incremental ledger, categorizes them (optionally via the host LLM), and auto-generates/registers new Hermes skills from templates.", "useful": 3, "reliable": 4, "polish": 3, "creative": 4, "beyond": 4, "total": 22, "best": "A creative 'GitHub stars into reusable skills' pipeline with correctly-implemented secret handling (agent.secret_scope.get_secret, never raw env reads, verified by its own tests) and genuine new-skill-registration capability.", "worst": "The README and code comments are saturated with self-referential rule-ID justifications (e.g. 'R05', 'R11', 'R16') and a forensic git-log provenance dispute about a sibling project, reading like it was engineered to satisfy an automated catalog-rule checker rather than to explain the plugin to a user \u2014 a polish/trust concern worth a human judge's attention.", "standout": false, "blocked": null}, {"pr": 153522, "name": "hermes-sfx-forge", "does": "A deterministic procedural sound-effect synthesizer that generates short one-shot WAV files (hits, pickups, etc.) from named presets and an integer seed using real DSP, then verifies output against a fixed numeric QA gate.", "useful": 3, "reliable": 5, "polish": 4, "creative": 5, "beyond": 4, "total": 25, "best": "Strongest security posture reviewed: path-traversal and symlink-attack defenses (O_NOFOLLOW, dir_fd-anchored opens, advisory locks) backed by a dedicated adversarial test file, plus fully deterministic, reproducible-by-seed audio generation with zero network/credential surface.", "worst": "Narrow usefulness \u2014 only game-sound generation, Linux-only (explicitly unsupported on macOS/Windows because of an fcntl dependency), and no visual demo since audio output isn't screenshot-able.", "standout": true, "blocked": null}, {"pr": 153880, "name": "quick-eval", "does": "After an agent reply, sends the user's last question to other configured models (cloud or local) for a side-by-side second opinion, lets the user mark good answers, and logs results for a growing personal eval dataset.", "useful": 4, "reliable": 5, "polish": 4, "creative": 4, "beyond": 4, "total": 25, "best": "Requires explicit one-time user permission before calling other models, uses parameterized SQL with a read-only connection, and has a real end-to-end test that spins up an actual Hermes subprocess plus a fake model server.", "worst": "No screenshots/visual assets found beyond demo-GIF test scaffolding, and 'comparing LLM outputs side-by-side' is a known pattern even if the zero-config chat-command UX is a thoughtful original touch.", "standout": false, "blocked": null}, {"pr": 152934, "name": "mission-control", "does": "A live, read-only observability dashboard for Hermes Desktop that streams tool calls, model calls, subagents, and approval events into a cost/token meter, call waterfall, and loop detector.", "useful": 4, "reliable": 5, "polish": 5, "creative": 4, "beyond": 4, "total": 26, "best": "Purely observer-based (8 lifecycle hooks, 'never written to: no tools, no middleware, no approval answers'), every hook fails open, no credentials or network calls at all, and ships a banner image and dashboard screenshot plus a Node-based UI smoke test under React 19.", "worst": "It adds no new agent capability beyond observability \u2014 useful for operators but not something that changes what the agent itself can do (lower on 'beyond a prompt' than plugins that add real tools/providers).", "standout": false, "blocked": null}, {"pr": 150810, "name": "tone-forge", "does": "Generates guitar-amp tone recipes from natural-language descriptions or reference-audio analysis, stores them as versioned presets, and can send real MIDI Control-Change messages to drive AmpliTube 5.", "useful": 3, "reliable": 4, "polish": 5, "creative": 5, "beyond": 5, "total": 27, "best": "Genuine hardware integration (ctypes bindings to winmm.dll for real MIDI I/O, a hand-rolled pure-Python FFT for reference-audio analysis) with careful safety design: MIDI never sent to an unselected port, sends labeled 'unverified' rather than claiming success, and SSRF-guarded URL/subprocess handling for reference-track fetches.", "worst": "Niche audience (guitarists using AmpliTube 5 with MIDI gear) and the README itself admits no screenshots or recordings are committed yet and that actual AmpliTube receipt of MIDI messages hasn't been verified on the build machine.", "standout": true, "blocked": null}]}