Plugins

Per-model system prompt injector for DeepSeek Harness: append custom prompt text to the END of the system prompt for locally configured models, matched by exact provider/model route or a provider-wide provider/* rule (both stack in order). A Settings page lists every configured provider and its models for per-route editing with instant effect, and rules persist to DSH_HOME so they survive restarts. Applies to main sessions, subagents, and workflow children alike.

Combines fault knowledge-base symptom-to-cause rules with similar past cases to rank candidate motor diagnoses with evidence terms and suggested extra tests.

BaziDIY ontology plugin: deterministic bazi/wuxing/bead/style rules as DSH tools (calculate_bazi, propose_designs, generate_design, save_design, load_design), plus bracelet SVG rendering and a bead editor; no LLM calls inside execute.

Answers hard questions by staging a formal debate: two adversarial subagents argue opposite sides with research, then the main agent rules on the transcript through the debate_open, debate_round, and debate_verdict tools.

Session handoff for DeepSeek Harness: the session menu creates a successor session that rebuilds the old session's memory, tasks and rules through an eight-section takeover packet, with light context via on-demand transcript readback.

Clean Architecture reference library for DSH: 8 pinned reference repos (Go, Java, C#, Python) indexed into a local FTS5 database, with assertion rules, a review ledger, and a read-only observation panel.

Turns code review into a hard gate: deterministic severity rules, LLM-assisted findings, a team approval quorum and a durable compliance audit trail that must pass before a merge proceeds.

DeepSeek Harness web client plugin: group sidebar workspaces into a configurable three-level tree (分类→项目→会话). Sidecar YAML rules. dsh-plugin.

Hybrid model router for DeepSeek Harness: declarative rules, user-configurable cost control (cost-first / quality-first / balanced), optional LLM task classifier, and failure fallback chains.

Appends ambiguity-handling rules to the dsh system prompt so the agent asks clarifying options before guessing.

Static HTML auditor for Chinese line-breaking: checks explicit-`<br>` orphan lines, keep-all CSS coverage, CJK line-start/line-end punctuation rules, and protected-phrase splits, then inserts <wbr> at natural breakpoints; exposes a cn_linebreak_audit tool for agents.

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.

Permission mode between workspace-write and full access: shell commands are checked by deterministic rules and a subagent review; irreversible or system-level actions require explicit approval.

Rules, commands & skills manager for dsh: /rules slash command, settings panel with visual rule editing (add/edit/disable/delete, free-zone support), user-defined custom commands with {input} arguments, skill management, and automatic backup & one-click restore of AGENTS.md.

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.

A 轨迹解读 (trajectory interpretation) tab that summarizes each user round — what was wanted, how the assistant thought and executed, files/commands/errors — via a rules engine plus optional LLM narrative; user messages stay verbatim.

Read-only Claude Code compatibility bridge for DeepSeek Harness: Skills, Rules, command Hooks, and Agents from .claude as SSOT.

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.

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.

Deterministic code security review: 40+ rules, secret entropy detection, staged-diff review, SARIF export, baseline acceptance, SBOM-lite dependency inventory and health self-check.

Autonomous permission classifier for the auto preset: tool-scoped allow/deny rules, an LLM semantic judge, and git checkpointing for unattended sessions.

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.

A project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify→commit→push→review→close sequence. One skill instead of the same rules copy-pasted into every agent's instructions.

Measures design rules on the rendered page rather than in the CSS — type-scale count, WCAG AA contrast against the real composited backdrop, spacing-grid drift, palette size, tap targets, and the tells of generated UI such as violet gradients caught by hue angle; ships a design-system skill.