Plugins

Automatic approval and review for tool calls that need approval: keyword buckets match red lines without context, then a judge model classifies what was requested and sends it to allow, reject or a human according to the matching row and risk level; a judgment that never ran always goes to a human, and rejections tell the model why.

Bayesian stock prediction plugin that fuses MACD, RSI, moving-average, volume and other technical signals into an up-move posterior probability with multi-horizon comparison, trend-state classification and position risk metrics for A-share and US stocks.

Interval heartbeat that wakes each root agent itself (followup injection) to proactively report progress, risks or blockers: busy-safe queuing, no stacking, auto-pauses when no human replies, re-arms on the next user message.

English edition of Weiwen's Law (KISS's Law): the first and only domain-agnostic white-box causal adjudication middleware for AI agents. Unlike domain-specific causal-inference tooling (statistics/economics/ML) or evidence-gated agent firewalls, it adjudicates *every* tool call along a deterministic structural causal chain (R->S->D->H->M) before execution - across any domain, with no training or per-domain tuning. It blocks destructive and credential-file operations, escalates repeated boundary violations, cuts faulting links until verified-fixed, and gives risk verdicts on un-auditable execution; runs fully local with zero API cost.

Pre-visit due diligence and company research in DeepSeek Harness for customer background checks and risk briefs, with Qichacha MCP tool-call budget approval and entity confirmation.

Insurance company operations analyst — runs real solvency, profitability, embedded value (EV), investment risk and regulatory compliance calculations, not just text explanations.

Vets local, npm, and GitHub plugin source before installation, blocks configured high-risk tool calls at runtime, audits output secret patterns, and writes HMAC-chained local audit logs.

Source-aware prompt injection guard for DSH: tracks untrusted turn context, detects injection signals, scores sensitive sinks, and blocks high-risk tool calls with explainable audit logs.

Plugin-combination analysis for the DeepSeek Harness: dependency trees, conflict detection, risk scoring with prediction, visualization, and combination simulation.

Quality-aware in-agent plugin discovery: a find_dsh_plugins tool that ranks the whole dsh-plugin topic through a daily quality-scored index (installable manifest, curated listing, license, activity) merged with a live gh search — zero LLM API cost, risk flags and exact install commands in every result.

Adds an Explain button to the approval card: one model call returns exactly three lines reading the pending operation, covering what it does, which files or system state it reads, writes, modifies or executes, and a risky/attention/safe verdict with a one-sentence justification. It also renders the detail area for `write` and `edit` calls, which the shipped renderer leaves blank because it only reads a `command` field.

TypeSafe Jev (System One decision model) for DeepSeek Harness, end to end: jev_decision (choice/score/noul, parallel, typed answers + confidence), a Settings > Plugins card for the API key and switches, inline tool views showing every decision in the conversation (answer, confidence, latency, cost), an auto-guard (deterministic + Jev risk/loop checks), a local /jev dashboard, and an online verification benchmark (96.3% on 27 labeled questions, median ~283 ms on jev-latest, 2026-09-21). Honest by design: real API only, no mock fallback.

Manage VPS servers over SSH key login: 21 zero-token /vps- commands (status queries, recipe installs with a plan and /vps-yes confirmation, reboot that waits for the machine to come back), an in-conversation terminal (xterm.js over ssh -tt) for interactive programs, 5 agent tools with risk-tiered confirmation, file backup with automatic restore and a firewall/SSH safety net, 29 built-in recipes, and a settings page for adding machines.

Delete sessions from the DSH Web sidebar: adds a Delete action to the session row menu with a risk-consent dialog, then removes the session log, workspace accounting and live session state.

Language-pack framework that rewrites model replies: A is an independent LLM rewrite, B injects FTS5 terminology retrieval into that rewrite, C applies local dictionary and regex rules, and composite runs a pipeline such as B then A then C. Ships a GitHub pack marketplace, a ZIP installer with path, size and file-type checks, and a mandatory risk disclaimer gate.

Stability audit for installed dsh plugins: static risk grading (hook surface, startup work, inject, entry, dep ranges) plus optional isolated install verification.

Security-focused Feishu (Lark) channel for DeepSeek Harness: allowlisted remote-agent access with workspace-scoped paths, symlink checks, risk-based approvals, session isolation, redacted logs, and bounded message queues.

Task-aware DSH plugin navigator: builds a local index from GitHub topics and community lists, retrieves across 28 bilingual capability classes, and provides commit-level static risk audit, consent-gated pinned installation, composition checks, and recovery.

Falsification-driven correction loop for agent sessions: risky work commits an evidence-checkable claim first, deterministic gates verify it, falsified claims force mutually exclusive replacement hypotheses with discriminating experiments, and every event lands in an append-only evidence ledger.

Provenance-aware execution security for DeepSeek Harness. Track sensitive data across tool calls and stop risky side effects before execution.

Codex-style approval autopilot for DeepSeek Harness: ordered glob rules (allow/ask/deny) plus an AI risk judge (low/medium/high) mapped through a risk tolerance, as an approval answerer.

Destructive-command interception gate for dsh: parses shell semantics, judges risk against 41 built-in rules, and holds irreversible rm -rf, git reset --hard, and git push --force style commands at a confirmation gate.

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.

Update copilot for DeepSeek Harness: one scan covers the DeepSeek Harness core and every profile plugin; explains what changed and how risky each update is, then updates only what you confirm.