Plugins

Plugin trust pipeline for DeepSeek Harness: deterministic static scan with verdicts, opt-in runtime guard with honeypot lures, agent audit-protocol skill, and a browser shield status light. Alarm-only, never an enforcer.

Tested-curation lab for DSH plugins: every entry passes real install/static-scan gates in an isolated environment, with full logs and reproduction commands (Chinese-first).

GitHub search, discovery and audit scripts wrapped as a SKILL.md pack around the gh CLI: repo search, multi-axis explore, trending, repo summaries, similar projects, code search, issue/PR search and org audits; ships as a dsh bundle (and on npm).

GPT plans dependency DAGs, DeepSeek workers execute tasks with adaptive parallelism, and an optional GPT reviewer audits incremental Git diffs and drives repair rounds.

Biomimetic memory system for DeepSeek Harness: plain-Markdown data layer, memory tools, frozen-snapshot injection, graded approval gating, structured audits, memory metabolism (dream), memory pins, semantic recall, /memory command, and cross-session retrieval.

Reviews every file the agent wrote in a session from the session header, with per-file hunks and refused writes counted apart from changes.

Optionales Provider-Plugin für dsh-skill-pack-security: registriert die skills/-(zh-)oder skills-en/-(en-)Edition des Pakets in ctx.skills. Liefert beide Editionen eingebettet in pack/.

Erstellt prüfbare Wissensdatenbank-Pakete (SQLite FTS5) aus md/txt/docx/pdf mit deterministischem Retrieval und Lesen des Originaltexts.

Local semantic-token theme editor with palette extraction, WCAG auditing, preview, and export.

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

Ecosystem-wide plugin health audit: syncs the dsh-plugin topic into a local scored catalog (maintenance / docs / npm + weekly downloads / ecosystem, 0-100, A-D), static security scan with high-finding grade veto, star history snapshots, web leaderboard and agent tools.

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.

Rules execution engine for dsh: parses AGENTS.md, hard-blocks rule-violating tool calls, text-based B/D rule auditing, /guard command, version-guard for versioned files, and free-zone support (engine skips free-zone sections).

Document-code consistency guard: audits version headers / changelog tables / directory trees / module & test counts / cross-doc references for drift, with severity-sorted, read-only fix suggestions.

A structured multi-panelist review workflow for the DeepSeek Harness: N panelists score in isolated subagents, blind to each other; a chair reconciles disagreement by anchor match then Δ-level adjudication; an independent critic audits the process. Works for design, code, paper or project review.

Turns the iterate skill into an autonomous closed-loop harness — plan, parallel review, atomic fixes, validate, loop, auto-stop — plus a dry-run review-only mode and a meta-review that audits the report and emits a final review report.

Mojibake guard bundle for DSH: feature-based garbled-text detection before writes with review-then-release (an identical retry passes), plus pre-execution pwsh encoding audit (ANSI/GBK/UTF-16/Default), Windows and Chinese first.

Evidence-first vulnerability research workbench for DeepSeek Harness: native audit views, 29 OMV tools, Evidence.v1 findings, reproducible runs, Campaign workflows, and isolated PoC evidence.

Replay sessions on a playable timeline with per-step token usage, audit sensitive operations, estimate cost, view fork lineage, compare sessions, and export standalone HTML replays.

Pixel-art whale desktop companion with 29 frame-audited states — taps the glass and flashes the tab title when an approval waits, speaks a completion report when a turn ends, and adds a slash-command palette to the web client.

Zeigt die DeepSeek-Harness-Plugin-Liste nach Quelle gruppiert an — offizielle Plugins und selbst installierte Plugins auf einen Blick.

Audit-Panel für den Harness-Ereignisstrom: beobachtet Ereignistypen, Verteilungsmuster, Zählungen und die jüngsten Ereignisse und hilft Plugin-Autoren zu verstehen, was intern im Harness geschieht.

Der Plugin-Manager `dsh pm`: Suche über mehrere Quellen (Awesome-Liste + GitHub + npm), Installieren/Entfernen/Aktualisieren je Profil sowie ein Doctor-Audit von Manifesten, Bundle-Patches und Versionsabweichungen.

Schreibgeschütztes Audit der Zugangsdaten-Hygiene der Agentenflotte: Berechtigungen von Zugangsdaten-Dateien, eingebettete Zugangsdaten in Git-Remotes (in der Ausgabe maskiert) und Anzahl wörtlich vorkommender Provider-Token; abhängigkeitsfrei und deterministisch.