Plugins

Software-engineering method pack for coding agents, with skills for baseline-first planning, systematic debugging, prompt hygiene, verification before completion, and repair/retirement tracking.

Superpowers for DeepSeek Harness: TDD, debugging, planning, and collaboration skills adapted from obra/superpowers, installed as a Cordis plugin registering 14 skills with zero runtime dependencies.

Engineering workflow system for AI coding agents — mandatory planning, TDD, verification, review, and intelligent codebase graph analysis.

Complete port of obra/superpowers for DeepSeek Harness: 14 methodology skills via a native SkillProvider (rank 550), covering brainstorming, planning, TDD, debugging, parallel agents and more, with Chinese-localized docs and zero-build install.

Modular frontier execution discipline for DSH: evidence-first routing across 26 skills, Manus-style file planning, verification gates, fail-streak recovery, and an interactive web dashboard.

Coordinates Codex planning and independent review while the original DSH session implements and tests changes.

Context Assembler plugin for DeepSeek Harness: topic-block context assembly, water-pressure topic splitting, tool trace/rewrite, reality recall injection and handoff planning.

Per-workspace project kanban board: nine kanban_* model tools for agent-driven planning plus a browser board UI, with disk persistence, undo, templates, and archiving.

Grok-compatible web search with retained source pagination, Context7 and Exa documentation lookup, bounded page extraction, site mapping, offline research planning, and read-only diagnostics.

Registers a SpecWorkflow skill pack for requirement clarification, implementation specs, execution, delivery review, repair planning, bug diagnosis, and source-backed research.

Local-first AI project orchestration workbench and CLI plugin for DeepSeek Harness: approval-gated planning, Git worktrees, task execution, Issues, and auditable evidence.

Map and routing tools: driving/transit/walking/bicycling route planning, geocoding and POI search via free OSM/OSRM data by default, with an optional Amap (高德) key for better China coverage.

Grok-compatible web search with retained source pagination, Context7 and Exa documentation lookup, bounded page extraction, site mapping, offline research planning, and read-only diagnostics.

Three-tier now/next/later input planning dock for the DeepSeek Harness web GUI: a red/yellow/green priority strip replaces the busy-Enter queue, plain Enter queues to later, with in-place multi-line editing, drag reorder, and session-isolated freeze/resume; the freeze button bridges a separate plugin, [dsh-session-guard](https://github.com/drscrewdriver/dsh-session-guard) (installable from dsh-market), via stopNextTurn/resume RPC + composer lock for a real per-session lock, pairing with its global peak-hour auto-pause to stop sessions during DeepSeek's high-cost windows and resume off-peak.

Adds persistent execution contracts, recursive work graphs, critical clarification, and evidence gates for long or underspecified Harness tasks.

Task planning with experience muscle-memory: condition-reflex recall of past solutions, LLM capability matching, and auto-persisted lessons.

Model switching and reasoning-effort control for DeepSeek Harness: set_model and list_models agent tools let the agent autonomously change its provider, model or thinking depth (reasoning effort) mid-task with a mandatory reason, a provider whitelist and a context-window token-pressure guard, the active model is injected into the runtime context, and Plan Mode auto-transition switches to a configured planning model on entering plan mode and restores the previous execution model on exit.

Insurance product comparison & proposal expert — clause analysis, cost-effectiveness, coverage planning, generates verifiable client-facing PDF proposals.

Ports the obra/superpowers methodology as 14 native DSH skills covering planning, TDD, debugging, and code review.

Cordis-native, evidence-driven full-stack engineering workflow: inspect-first planning, explicit verification evidence, and approval-aware gating for sensitive operations.

Nearly half the agent cost, with accuracy intact. Just enough tools is a DeepSeek Harness plugin that uses Jev to reveal tools and skills progressively. The main model starts with a clean planning step. Jev then selects which capabilities to add as the task unfolds.

Mind-map project planning with blocking drift protection: plans, modules and tasks as a dependency DAG with topological execution order, an agent position marker, a human approval gate on every board edit, git cross-checks, and evidence-gated task completion.

Conversation-level multi-agent workbench for editable task planning, real child-session observation, plan-versus-runtime comparison, and evidence-backed recovery previews; tested with DSH 0.1.1-rc.2.

Verifiable issue-to-PR delivery chain: an 11-stage pipeline (analysis, search, code understanding, hypothesis, planning, implementation, patch ledger, tests, review, failure classification, PR build) with 4 human review gates, GitHub/GitLab/CodeArts credential connections, a 5-page workbench and a draggable AI assistant panel.