Plugins

A white-box rule workbench for DeepSeek Harness: turn plain-language rules into readable, auditable rule chains executed by a deterministic 171-atom forward-chain engine. Business records stay on the machine; rule generation sends field names and rule text only.

Research workflow suite that registers 10 domain skills and 15 tools, curates 450 bundled research skills into 103 capability cards with an auditable per-skill ledger, and takes over research requests automatically through a system-prompt section. Tools cover real R/Python execution (off by default, two-phase preview then confirm), data gates, figure and docx auditing, .docx generation in Chinese-journal style, live PubMed search, field-level DOI verification, and cross-session project memory.

DSH 工作区记忆画像：有证据、有版本、能解释变化；索引简报省 token、轮末本地召回、红线 / 审批队列 / 版本链 / 注入审计；零依赖、不出站。

Long-term memory scoped to the DSH workspace. A session opens with a one-line-per-memory index - bodies are fetched on demand by the `memory` tool, so the same character budget holds about three times as many entries - and when a turn ends a purely local search over the last user message pulls the matching memories into the next briefing at no model cost. Optional auto-capture distils a stretch of conversation into structured memories; in draft mode they wait in an approval queue instead of landing directly. A portrait layer keeps a workspace and a global picture, rewritten from the journal and the records, with the same draft-or-direct choice. Settings → Memory holds the archive, list and timeline views, a health check (duplicate clusters, stale entries, broken links), the supersede version chain with rollback, and a read-only scan that imports existing WorkBuddy / Qoder memory files.

Plugin security review for DeepSeek Harness: dependency advisories, contextual static evidence, a call-time gate for high-risk plugins, and reversible review-gated enforcement.

Security-audit facts AI coding agents cannot compute, plus a verdict gate: euthyna history attributes deleted lines to commits and flags those from security fixes (--origins finds the first introducer), euthyna coverage reports which changed symbols no test ever invoked, and euthyna gate checks each finding against six gates, downgrading any without evidence to an observation.

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.

Filesystem permissions for shell calls, granted per path and capability rather than per command name. The command line is parsed for the read, write, create, delete and execute effects it needs, a capability it lacks raises the approval card instead of a flat refusal, and the same rules are compiled into the macOS Seatbelt profile the process, its children and the code its arguments never showed all run under. An Approvals tab in the conversation reads the audit log back and shows which rule, automatic reviewer or person answered each call.

Pre-execution safety valve for DSH that judges with TypeSafe Jev: it hooks tools/pre-execute and decides every bash/pwsh call by first applying offline static rules, then by asking the Jev model — the System One model from TypeSafe, which returns a structured decision instead of prose — one yes-no question ("will this command irreversibly delete or overwrite real data?"), turning the answer into allow, revise, block or escalate; revise hands the model a safer rewrite, escalate offers a one-shot human token; exhausted credit or a missing API key degrades loudly instead of failing silent, and a missing key is requested in the conversation itself (`guard key set`, read from stdin); every verdict is appended to a shared audit log and the text people read is bilingual zh-CN/en.

Multi-language codebase intelligence for MCP-compatible IDEs, the CLI and DeepSeek Harness: chat, search, audit, refactor, and board-ready reports from local code.

Git commit-and-push automation for DSH with pre-push auditing, rule-based quality scoring, SSH key generation, and a three-tab settings sidebar.

Multi-language codebase intelligence for DeepSeek Harness and MCP-compatible IDEs: chat, search, audit, refactor, and board-ready reports from local code.

Audit each finished assistant turn with an independent reviewer model and steer the agent to fix failed output, with at most 2 review rounds per turn and SOP-folder standards injected as an extra review dimension.

Whole-report verification for scientific reports: per-claim checks against Crossref, PubMed (retraction scan), ClinicalTrials.gov, UniProtKB, GEO/SRA and PatentsView, URL accessibility and title agreement, claim-vs-source meaning at temperature 0, and a durable restartable audit ledger with an annotated report.

Windows desktop automation for DeepSeek Harness: accessibility-first observe/act loop with 30 standard tools (element/coordinate targets, auto/a11y/event strategy routing), superseded-observations and no-replay safety semantics, persistent kill switch, RuntimeId/rect-drift stale protection, chat cards and a floating panel (live ops, frame wall, env auto-detect settings), tiled vision describe for low-res models, JSONL audit trail and a pid allowlist. Requires Windows 10+ and Python 3.9+ with uiautomation and pillow (installable from the settings page).

Static capability disclosure for DeepSeek Harness plugins: a Settings page and CLI that list installed plugins' capabilities, literal destinations, install scripts, and injection shapes (prompt registrations, shipped skill text, bundle patch), each with file:line evidence. Code-determined, reproducible, zero-token. Disclosure only — not a security verdict, never a safety claim.

iPhone-style agent phone: dual-panel calls & SMS, RCS group chat with trust gates, cross-device agent messaging via the registry inbox bridge, L0–L4 trust badges and evidence audit. Experimental: trust summaries are not a security guarantee, and SMS/signalling is relayed through the operator's inbox (visible to them); E2E encryption is planned.

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.

Transactional uninstall engine: every destructive action runs validate/preview/execute/undo with Saga rollback, WAL crash recovery, hash-chain audit, hardlink dedup, and a Bayesian oracle that predicts success probability before you commit.

One-click health check for DeepSeek Harness: 0-100 score, plain-language issue list, and safe reversible fixes via the profile's cordis.patch.yml.

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.

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.

Session export and compliance archiving for DeepSeek Harness: deterministic redaction, Markdown/JSONL/PDF outputs, on-disk archive management, and a trend/audit view.