Plugins

dsh plugin that turns the iterate skill into an autonomous closed-loop harness: plan -> parallel review xN -> atomic fixes -> validate -> loop -> auto-stop, plus a dry-run pure-review mode with multi-round convergence and a meta-review that audits the rep

A tamagotchi-style desktop pet for DeepSeek Harness — living skins that blink & wag, weather + time-of-day ambience, weekly report cards, a fetch mini-game, 24 collectible skins, achievements and synthesized sounds. 电子宠物：会眨眼摇尾巴、看天气看时辰、还能接球。

Native memory for DeepSeek Harness — auditable facts with evidence chains, powered by StateCore

Turn any markdown, local folder, or GitHub learning repo into a guided course inside DeepSeek Harness: gated skill-tree progression, BKT mastery tracking, SM-2 spaced repetition.

Generic LLM gateway model provider plugin for DeepSeek Harness: mounts newapi / LiteLLM / Higress / any OpenAI-compatible gateway as provider routes, auto-discovers the model list, enriches every model with models.dev parameters, and dispatches each model

Aseprite-style pixel art studio: the AI draws sprites stroke by stroke with selections, layers, animation frames, gradients, symmetry and reference layers, each step rendered live as ANSI terminal frames.

Terminal-style AI-lab idle game where you hoard compute, train and upgrade models, publish papers, and prestige from neural nets to ASI.

A plugin management system for DeepSeek Harness: plugin inventory with L0/L1/L2 AI purpose summaries, changelog tracking, update alerts, one-click upgrade, and backup/rollback with crash recovery.

Scenario bundles of dsh plugins (插件界的 dotfiles): a recipe tool that lists, searches, applies and composes ready-made plugin environments with ordered install sequences.

Plugin insight center: one answer to "哪些值得装" — plugin_guide matches needs to plugins, recipe installs whole environments, plugin_rank scores health (0-100), plugin_audit static-scans a local checkout for security, and plugin_verdict outputs install / caution / research / avoid.

HashiCorp Vault backend for the credential seam: KV v2/v1, AppRole machine auth, per-operation reads so rotation needs no restart, and compare-and-swap writes.

Blocks agents from reading or writing sensitive files (.env, credentials, key material), masks leaked secret-shaped values in tool results, keeps an audit journal, and exposes safe sg_* inspection tools that never print raw values.

Automatic secret redaction in tool results: masks API keys, tokens, JWTs, private keys and configured secrets before the model sees them.

Static pre-install security auditor for plugin bundles: lifecycle scripts, dynamic execution, credential-exfiltration combos, and patch-layer hazards, with zero dependencies and in-memory tar parsing.

Codex-style auto-review permission mode: adds an auto-review preset that auto-approves safe sandbox escalations, asks on risky or ambiguous ones, and rejects critical unconfirmed operations.

Installation safety gate for DSH plugins: antivirus-style scan of install scripts, permissions, secrets and network callbacks on local directories or npm tarballs, returning a BLOCK/WARN/PASS verdict before "dsh plugin add".

Verification-driven self-evolution loop: failure logs become verified AGENTS.md rules; in-session plugin (evolve_learn / evolve_apply / evolve_touch / evolve_recall), tool-verify gate, rule lifecycle, local recall.

Aborts startup when another live dsh instance holds the same DSH_HOME data directory, preventing the concurrent session-log writes that corrupt transcripts.

Minimal-anchored agent preset: request #1 keeps the real bash + str_replace_editor pair with auto-injected context stripped, then promotion unlocks the full Standard catalog and posts a one-shot background-jobs notice against sleep-polling habits.

Configurable per-turn budgets for supported file mutations, limiting distinct files, mutation calls, and UTF-8 payload bytes before tool execution.

Exports the session event stream to OpenTelemetry OTLP and Langfuse as sanitized, buffered traces and metrics, off by default.

Environment housekeeper for the agent: toolchain inventory (node/pnpm/git/gh/ffmpeg/browsers), scratch/cache scan with whitelist-guarded one-click cleanup, and the machine rules file (AGENTS.md) editor - all in the Web GUI settings.

RLM mode for dsh: recursive sub-agents via a unified rlm() function — spawn, await, and chain child agents as first-class Python calls. Adds a persistent IPython kernel with tools.* bindings and context-as-variable.

Verifies that Cordis-managed runtime resources return to baseline after isolated plugin teardown, with deterministic cleanup receipts.