Plugins

Hierarchical Claude Code-style memory: user + project scopes (project memories committed to git for the team), MEMORY.md index auto-injected at session start, context-window guards, pure files.

Fail-closed runtime tool-call loop guard for DeepSeek Harness.

ICVO coding-standards kit for DeepSeek Harness (formerly dsh-coding-kit): a bundle plugin that registers tools on load and injects the standards only when apply_coding_standards is called, plus a P0 gate CLI (npx spec-wave) with G1-G7 process commands, skills install, host apply, and IDE-block refresh.

AST-based context compression, test log filtering, and token budget guard for DeepSeek Harness: strips redundant syntax, prunes noisy log lines, and enforces a token ceiling so the context window never overflows.

Redirects DSH downloads, artifacts, caches and temp files to user-specified drives (auto-picks the largest non-C drive), injects a path-discipline prompt into every session, and ships a disk_guard tool for status and cleanup — keeps the C: drive from filling up.

DeepSeek Harness bundle wiring the @forgeax/game MCP server, its bundled ForgeaX Skills, and a workspace guard into a DSH profile.

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.

Two-tier model routing: a strong tier plans, advises and reviews while a cheap tier implements, with plan-mode-aware auto routing, a high-impact escalation guard, failure auto-escalation, and subagent tiering.

Self-evolving pitfall immunity for coding agents (Claude Code, Codex, Cursor, ZCode, DSH): capture failed-then-fixed tool episodes as SQLite+FTS5 antibodies and inject them before the agent repeats the mistake. Zero runtime dependencies.

Per-conversation system prompt studio for DeepSeek Harness. Append text, shadow-replace one named first-party prompt section, or replace the whole system prompt; changes apply on the next model request without a restart. Overrides persist per session and are inherited by forked conversations along the parent chain, with a Pin action to freeze the inherited result locally. The panel lists the real assembled sections and guards unsaved edits.

DSH plugin bundle: workflow skills, engineering presets, independent better-goal / better-subagent / better-compact / better-ask-user integration, and a minimal job exit guard. Pure ESM, no build step.

Agent state machine plugin with a todo ledger, stall guard, phase trails and a process-isolated per-step Python worker with GUI automation lanes. Windows only; needs Python 3.10+ on PATH, and pyautogui, mss and pywinauto for the GUI lanes.

AX-first macOS computer use for DeepSeek Harness: accessibility snapshots with stable refs, background input, Unicode typing, menus, apps, set-of-mark screenshots, on-device OCR, verified actions, and optional Jev (TypeSafe System One) semantic guards — 1

LAN access for the official DSH Web UI through a gated reverse proxy: DSH keeps its own loopback binding, and a second port adds a password gate, self-signed HTTPS and per-device pairing that can be revoked individually, with a QR code to open it from a phone.

Peer communication between conversations in one DeepSeek Harness process: list the conversations the workspace shows, link one under a nickname, message it without waiting for its turn to end, read its progress without waking it, and declare rules for your own tool calls.

Plugin governance: new/updated plugins stage in a candidate area first, then hot-mount after startup — success promotes, failure auto-disables, repeated failures freeze, one-click safe mode, sidebar diagnostics panel (npm: `bsfeng-dsh-guardian`).

Browser notifications and a beep when a session turn ends, the agent asks a question or approval is pending; clicking the notification jumps to the session; remote trigger endpoint and SSE channel (npm: `bsfeng-dsh-notify`).

Concurrency guard and monitor for DeepSeek Harness: FIFO queue when concurrent model requests reach the limit, per-day persisted stats with error-kind classification, and interruption detection for abandoned streams.

Agent security guardrail: intercepts and audits every tool call, requiring human confirmation on sensitive operations.

Tool-use visibility for dsh: an act wrapper and guard make every ordinary tool call carry a describe field (direct calls are rejected by default), the model narrates decisions in plain text, and live act cards with thinking, purpose, status and result show in a strip under the composer and, with the optional dsh-better-sidebar plugin, in a right-side digest panel. Also adds a background event tool for long tasks.

Self-evolving pitfall immunity for DeepSeek Harness: capture every failed-then-fixed tool episode, distil it into a reusable antibody stored in SQLite+FTS5, and inject the relevant ones before the agent repeats the mistake.

A ZCode-styled skin for DSH Web: Zai light/dark themes, sidebar workspace session tree, global search, turn navigation with hover wave, and approval-card / message-keycap styling aligned to ZCode — every visual value guarded by contract assertions. A fork of MichengAI/dsh-codex-ui; do not install it alongside the upstream plugin — both repaint the same sidebar and conversation surfaces.

Two gates for outbound AI text. (1) Guard: before any text goes out it blocks the shapes anyone could write — padding verbs plus abstract nouns ("optimised the code structure"), hollow adjectives, universal filler, template openers, git commit/PR/review boilerplate, comments that narrate the code. Covers chat, comments, email, commit messages, PR descriptions, reviews, issues, docs and code comments. Passes with OK, blocks with one line naming what to change. (2) Catch memes: when someone drops a slang term the model does not guess or look it up — it already knows. A built-in 6792-entry meme wiki is queried before the model starts thinking, and the entry usage field ("how to answer this") goes straight into context. Matches only exact title/slug/alias hits, never fuzzy, so ordinary chat never triggers it. Bundled SQLite by node:sqlite, zero dependencies, 1.6ms per query. Settings page: guard on/off, strict mode, prompt section toggle, meme wiki toggle, per-turn auto-lookup, a four-step tone slider (reserved / measured / follow the room / unrestrained) that is behavioural rather than a label, AI-completion switch (off by default, uses the session own model so no API key needed), a paste-and-test box, and three thresholds. No model call for any check.

An always-on working style for DSH agents, packaged as an agent preset: restate the task, read before editing, verify each change with a real command, keep context lean. Ships 29 skills (plan loops, review loops, TDD, unsticking, PR watching) plus a turn guard that pushes back when a turn edits files without a successful check afterwards, and pushes back harder on a second miss.