Plugins

Static-only plugin gate and clinic for DSH: audit before install, hash-and-capability lock after install, local fingerprint peer search over GitHub topic:dsh-plugin, and mechanical detox. Never executes the target plugin.

GitHub account management plus a local Git workflow for the web GUI with clone, fast-forward pull, status, commit, push, and host-side push guards.

The task-center plugin set for DeepSeek Harness in one package: task ledger, model tools, human commands, wake patrol, quota-resume guard, idle-session mining, the reaper, scheduled sends, and the web kanban.

Reliable todo panel that survives restarts (official panel only re-renders on write — fixed via projection pre-warm) with three-state completion verification: evidence exists → verified, fake evidence → blocked, no evidence → unverified badge; settings toggle to fall back to official behavior.

Independent Codex Guardian-style approval reviewer for DSH.

Codex-style Git workbench: workspace-scoped changes, diff, stage, commit, guarded branch operations, graph history, fetch, fast-forward pull, and upstream push through official plugin APIs.

Usage statistics panel: silent per-model token collection, activity heatmap, trend charts, cost estimation and daily-limit guard.

DeepSeek Harness (dsh) approval answerer backed by the agent-governance sidecar — every approval/request is decided by the deny-by-default gate, L0–L4 rules and the organizational audit chain.

Checks git commit messages against the 7DGroup convention (Chinese type tags, length and punctuation rules) before committing, as a client-side guard before GitLab pre-receive hooks.

When a dsh turn gets interrupted — by a web restart or an upstream hiccup (rate limit, 5xx, quota error) — this plugin auto-injects a "continue" so your session picks up where it left off, with a dead-loop guard that hands back control if the retry produces nothing.

Tiered model routing for DeepSeek Harness: think/build model tiers, vision delegation (the vision model only describes images; the working model acts), image generation, and a high-impact guard.

Transactional data-only configuration pack manager with integrity, ownership, preview, diff, and rollback safeguards.

Auto-approval permission guard: a middle tier between workspace-write and danger-full-access — auto-allows safe operations inside trust directories, always asks a human for destructive ones, with 11 per-category switches and an audit trail.

Scans the DSH loader tree at startup for plugin conflicts (duplicate mounts, failed or pending plugins, duplicate config row ids), auto-stops or restores the affected plugins, and shows a conflict report popup in the web UI.

One-click start/stop launcher for DSH Web on macOS — start (foreground/daemon), stop, status, duplicate-launch guard, auto browser open, plus a Dock-able DSH.app built by script.

Commitment write-gate: operator-authored rules enforced before a tool call runs — a deterministic guard tier plus an LLM-judge tier, fail-closed by default, every block written to a contradictions log.

DeepSeek Harness community Bundle for the skill-security-guard static scanner

Guardian state engine for the DeepSeek Harness — assertion counting, edit review queue, and no-feedback-loop monitoring over session events

Self-protection guardrails for the DeepSeek Harness: protected-path interception, backup-before-destroy, CLI self-recovery commands, and strict sandbox defaulting

Pre-install supply-chain poison scanner for DSH plugins: AST (JS-X-Ray) + deobfuscation + regex heuristics, exits non-zero on findings for CI gating.

Runtime security gate on the tool pipeline: denies calls naming hosts outside an egress allowlist, redacts credentials from results at the canonical value rather than only the rendered content, and appends every decision to a JSONL audit log; ships in monitor-only mode.

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.

Static and runtime security guard for dsh: rule-based scans for malicious code, prompt injection and token waste, runtime interception of dangerous tool calls, /scan command, plugin_scan tool, web panel, and allowlist.

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