Plugins

Public/synthetic eval-pack lint and deterministic JSON grader; not a validated benchmark.

Read-only workflow panel for DSH: overview, six gates, milestones, org template, task flow and roster - project data from a project.json file, roster from the live DSH state, ledger presence from the ledger directory. Ships as a Cordis bundle with two GET-only routes and writes nothing to the project or the DSH state file.

Bilibili companion for DSH (MIT fork of Alterssss/dsh-bili-whale; do not install alongside the upstream — both register the same `/dsh-bili/` settings routes and share `~/.dsh/bili-whale.config.json`): wakes on a schedule, reads videos through subtitles, danmaku, hot comments and covers, writes two diaries, and shares at most one pick per wake by commenting on the video and @-mentioning the owner (daily quota 3; DM when `share.via=dm`). Inbound DMs, commenter names, summary requests and live danmaku are normalized and scanned for injected instructions before they reach the model; only the owner DM channel can carry an authorization prefix.

Emotion, energy and per-user portrait engine for AI characters: a 303-word emotion library scored in two steps (pick one of 6 categories first, then choose within it), novelty reward and same-word cooldown for diversity, a spirit meter with easter-egg state transitions (excited / suppressed / angry), and per-user portraits. File mode works with any AI; the optional OneBot mode reads friend message history from a OneBot 11 endpoint such as NapCat. Requires your own OpenAI-compatible LLM endpoint and API key (EMOTION_LLM_KEY or emotion/config.json).

Three ledgers for a model that loses context between restarts. Self-note: what I have become — capped at 40 entries, and every eviction first leaves a one-line crease recording which entry was dropped and why. Judgment ledger: record a claim together with how to verify it, come back when it is due, and mark it right or wrong; wrong ones stay in a mistakes book so you stop assuming you were always correct. Handoff: where this run stopped and what the next one should read first — a baton, not a memory. Three tools each taking an action parameter instead of a dozen separate ones (the prompt is paid every turn). Data lives in ~/.dsh/*.jsonl and is shared with the same-named CLI scripts. Zero dependencies.

One read-only index of every local AI-agent session (Codex, Claude Code, DSH, Trae, or any JSONL source) grouped by project, plus an append-only shared board for decisions and handoffs so switching agents leaves no context gap.

Named model routes for subagent delegations, configured from a settings page: each alias binds a subagent provider, model and optional reasoning effort, token cap, agent preset, tags, plus a "when to use" line the model reads to pick it, so a delegation names only the alias. Adds five tools (delegate, list routes, edit config, wait, release), shows the route a child actually ran on in its session header, lets each UI element be switched off, and keeps all configuration in one local JSON file instead of YAML.

Tracks token usage and estimated costs for every model call, with daily charts, session and workspace names, provider balances, budgets, and secret-free CSV/JSON exports.

Fairy III (Zenless Zone Zero) H.D.D skin for DeepSeek Harness: boot video, an eye-core dock that can be dragged vertically so it never covers text, and time-of-day greeting voices written by a model every day (5 lines, each <= 20 characters) and synthesized locally with GPT-SoVITS, with a fallback chain of today -> latest -> bundled audio so there is always something to hear. Replies can be spoken: a trailing marker line takes priority over length heuristics, and long replies can be compressed into one sentence first. The reader hashes the utterance it just played (MD5) so each reply is voiced exactly once, and switching sessions stays silent. Personal fork of dsh-fairy-zzz with its own package, route and storage namespace, plus a rate-limited summarize endpoint, POST-only engine control and bounded TTS and greeting caches. Two diagnostic logs (client revision, decision trace) are written next to the plugin and stay on the local machine. A personal fork of AssassinVIX/fairy-zzz-plugin (upstream package dsh-fairy-zzz): install this fork or the upstream, not both - both mount the full-screen skin on the same DSH surfaces. Dynamic greetings and spoken summaries need a DeepSeek-compatible API key in ~/.dsh/fairy-tts.json (or DEEPSEEK_API_KEY); without it only the bundled greeting audio plays.

Prompt manager for DSH: imports prompts from JSON or Markdown sources and DSH's own system sections, then controls what is injected into the system prompt — per prompt, or per agent preset — with title editing, drag ordering, LLM translation and the option to inject either the original text or its translation.

Delivery workflow preset for DeepSeek Harness: an agent protocol plus seven tools that keep user requests verbatim, record feedback decisions, plan tasks with acceptance criteria, log real verification commands and exit codes, and write completion summaries as per-project JSONL files.

Deny-only tool blacklist per agent preset. Tick a tool off in Settings and it leaves that mode's tool schema and its calls are rejected; nothing is ever enabled or whitelisted, and tools nobody denied are left alone. Each row expands to that tool's own description, and rules live in one JSON file outside the profile.

Token dashboard for DeepSeek Harness: per-provider monthly budgets, subscription quotas (GLM / Kimi Coding), account balances, and time-range cost and real-Token breakdowns — plus local JSON export and import for backup.

HireSeeker: поиск вакансий из Telegram-каналов и карьерных сайтов компаний. CLI/npx, JSON, skills для AI-агентов и плагин DeepSeek Harness.

反盲批 / Anti Blind Approval — DeepSeek Harness approval guard: review workspace-write escalation requests with the session model, then gate the Allow button on a strict JSON verdict.

Advisory permission checks for DSH tool calls: risk tiers, a path sandbox (empty allowed_roots denies every path-like call), a per-minute call limit and a JSONL audit, exposed through gate_check / gate_check_path / gate_policy and ctx.gate — other plugins or prompts must call the gate; it does not intercept tool calls by itself.

Event-driven trigger plugin (the doorbell beside dsh-proactive's alarm clock): recursive fs watchers with per-rule debounce windows and glob filters, plus a loopback-only local webhook endpoint with per-rule tokens, fire rules that wake a target session through the host agents service - live sessions get a direct follow-up, cold ones are resumed first - and inject a rendered prompt with template variables (paths, count, payload). Rules hot-reload from the event-gate rules file without restarting DSH, every trigger appends to an auditable JSONL history queryable via the trigger_list and trigger_history tools, and a loopback health route reports install and runtime status. Typical uses: auto-organizing a downloads folder, diagnosing CI or monitoring alarms posted from local scripts, and watching logs for errors. Pure JS, no build step, MIT.

Translate installed plugins' documentation into Simplified Chinese: README sections are translated with a persistent section-level cache, and an opt-in metaSidecars mode (off by default) writes a locale/zh.json sidecar for each Plugins list row so the list can render Chinese natively.

Reads the local NTQQ (QQ 9.9.x) message database on Windows and Linux and exports group and private chat history to txt, csv, json, md, html or sqlite. Ships sixteen model tools: qqnt_status and qqnt_doctor for environment and blocker checks, qqnt_extract_key, qqnt_index to build or inspect the sidecar index, qqnt_list_groups, qqnt_list_chats, qqnt_search, qqnt_stats for totals and monthly counts, qqnt_export_group, qqnt_export_chat and qqnt_export_batch (a chat can be named the way the user says it, and ambiguity refuses instead of guessing), qqnt_jobs for OCR, speech-to-text, chunking and model downloads, qqnt_media for a chat's downloaded images, qqnt_storage for disk usage and allow-listed cleanup, and qqnt_ask plus qqnt_recall for retrieval with citations. The local web UI on 127.0.0.1:46728 adds an incremental SQLite index, six views (chats, export, statistics, ask, settings, models), a task panel, a single-pane layout on narrow screens, sender redaction, media bundling, per-day splitting, export presets and AES-256 password ZIPs; OCR, speech and embedding components install into the plugin's own virtualenv on demand. Needs python3 with sqlcipher3 (the settings page can create a private virtualenv), and the database key is read from the running, logged-in QQ client.

Cross-session long-term memory for DeepSeek Harness: pinned rules injected every turn, the rest recalled by IDF-weighted keyword evidence, fact-key dedup, plain JSON storage, and a settings page to edit or delete entries.

Work todo reminders in a sidebar panel with four stage tabs (not started, in progress, overdue, done) plus separate recurring and paused filters, priority derived from the end time in real time, pinning that survives overdue, and enable/disable for recurring tasks. Recurrence covers workdays (following China's statutory holidays and make-up workdays), selected weekdays, monthly dates with month-end rollover, and 5-field cron; one-off tasks default to start and end reminders (start optional, end required); meetings can disable the end reminder. Alerts appear in a page overlay with optional browser notifications, snooze and quiet hours. Twelve agent tools; weekly/monthly reports, natural-language quick add, and cross-view search; data is a single local JSON file with completed tasks archived per quarter.

Sidebar todo list for DeepSeek Harness — grouped buckets, recurring tasks with weekday or month-day rules, a month-view calendar, and an agent tool that reads and writes the same JSON file.

Turn your recurring one-liners into capsules above the composer. They reorder themselves by how often you use them, and ask you to fill in {{placeholder}} values before the snippet lands in the draft. Clicking appends rather than replaces, so a half-written draft survives. A drawer adds search, grouping and editing, and everything lives in a Host-side JSON file you can edit by hand.

Per-package automatic updates for the DeepSeek Harness plugins you choose. On a schedule it asks npm for the latest version of installed plugins, updates only the packages you check, and skips local link or file installs, pinned versions and packages with errors; upgrades stay inside the major version and skip prereleases by default. Updates go through the profile's own plugin manager, so the profile write lock, pnpm step, bundle-patch validation and hot reload are the host's, and a failed install puts the previous version back. Each cycle is appended to a JSON log.