Plugins

A persistent multi-step task stack for DeepSeek Harness agents: focus_task / focus_complete / read_focus plus a /focus command, with zero automatic prompt injection

Context fullness bands, the per-session compaction threshold derived from the model window, per-step cost computed from cache read and cache write rates, cache-hit, DeepSeek balance with the peak/off-peak tariff, and a one-click handoff. It never calls a model and spends no tokens.

Prompt library stored in the plugin config, with a Settings page and a composer picker: the ticked prompts are injected into every model step of that session, and a subagent inherits the selection of its nearest ancestor session.

Clickable next-step suggestions under every reply; one click sends that sentence as your message.

Registers the dsh-mol stdio MCP server, built on RDKit with no network access, into a DSH profile. It exposes 12 tools: three-level SMILES validation with human-readable diagnostics and character positions, molecular properties, drug-likeness and structural alerts, structure rendering to PNG/SVG, multi-molecule grids, format conversion (SMILES, InChI, InChIKey, MOL, SDF, formula), standardisation with a per-step change log, deduplication, SMARTS substructure matching, fingerprint similarity, and batch clean-up that reports every rejected row. The patch only registers the server; the tools live in this repository's Python package and must be installed first — the README gives a `pip install` route and a from-source route, and until the package is on PyPI the from-source one is what works.

Per-project memory for DeepSeek Harness. Three Markdown files per workspace — PROJECT.md, DECISIONS.md and SESSIONS.md — are auto-created on the first step of any session in that workspace, re-read from disk and re-injected only when they change (and re-injected if compaction dropped them), and written back by classification through a memory_checkpoint tool, with a bounded end-of-turn nudge when a turn did work but recorded nothing. memory_read and memory_search read the live log and the archive, the latter over a zero-dependency BM25 index. The session log is capped at 200 entries with the overflow moved to SESSIONS-archive.md — never injected, but visible, readable and searchable, and restorable one entry at a time. Settings page: a workspace list with a path filter, read-only tabs for the three memory files plus the archive, reload, export/import of one workspace's memory as a JSON bundle, a two-step clear, a panel that rewrites or removes the AGENTS.md instruction block, and a PROJECT.md staleness reminder. A composer status chip shows that workspace's sync state and creates the files on click. Zero dependencies — no vector store, no embeddings, and no model calls.

Keeps a pool of models and routes every agent step to one of them with its reasoning effort set — configured by clicking in the composer, no JSON needed. The router takes over the composer's model cell, so one control shows the session's model and reasoning effort alongside the router's own settings. Three authorization scopes (model / effort / full) where a manual pick only counts in the scope that owns it, and in effort scope the router is bound to the one model you choose. Task presets with per-model weights, vision routing for image steps, session signals (active todo, context pressure, token budget, subagent depth), and an optional semantic task classifier. Thinking stays on, because DeepSeek rejects a thinking-enabled request whose history contains a tool call made with thinking off.

Workspace drift awareness for DeepSeek Harness agents: detects external/user file changes and injects them into the agent context at step boundaries.

Personalises the DSH running-turn status line: rotating bilingual quips, a configurable animated loading icon (5 styles x 3 sizes) and one-click matching to the active theme colour, all in a General-settings panel, plus a # Chinese / # English sectioned quips editor. Ships with no dependencies, no build step and no config file.

Process management: brings ntd-style processes (multi-stage, multi-step agent workflow templates) into the dsh web UI — browse, edit, validate, import/export and AI-generate processes; the built-in library is read-only while the personal library is writable with live file sync, and agents read the library through process_* tools and advance work stage by stage.

Archived-session manager: an "Archived Sessions" settings page that lists archived sessions and lets you restore or permanently delete each one (two-step confirmation).

Explicit cross-session work state for DeepSeek Harness: goals, decisions and next steps captured automatically from host events or via a model-visible work_state tool, inspectable with /checkpoint.

Adds a Reading tab to the DSH web client that shows process steps and live reasoning in source order, collapses successful turns to the final answer, and keeps the original tabs, composer, and tooling intact.

Draggable ring gauge showing live model output speed (tok/s) with an expandable per-step detail panel (exact speed, TTFT, cache-hit rate, cache read/write, reasoning and input tokens, model, cumulative tokens).

One-step GitHub uploader: initializes git, auto-creates or improves README, sets repository topics, and pushes a local project to GitHub.

Context manager for DeepSeek Harness: auto-summarizes every turn into priority-sorted records, injects them plus pinned cross-session notes and custom text into each model request, and folds any-size real conversation ranges into summaries to save tokens. Persistent and restart-safe. NOTE: manual multi-step install — copy the three package folders into profiles/node_modules and add the provided cordis.patch.yml rows, then restart DSH; not a standard one-command install.

Adds a Graph tab that renders one session's execution as an interactive DAG of turns, LLM steps, tools, skills, subagents, code changes and tests, with live status, retry aggregation, critical path and trajectory linkage.

Always-on ADHD-friendly output shaping: one system-prompt section makes replies action-first with numbered steps and concrete time estimates; adhd_on / adhd_off / adhd_status tools persist the mode across restarts.

Read-only Grafana tools that query metrics through the data source proxy: instance health, data source listing, instant and range PromQL queries, current alert state, and provisioned alert rules. Range queries downsample to a point budget; an explicitly supplied step that would exceed it is rejected rather than silently changed, so the model never receives data at a resolution it did not ask for.

Trading-terminal style cost tracker for DeepSeek Harness: sidebar balance and today spend, per-step RMB cost table, auto-synced official pricing with peak/off-peak, cross-session and per-day summaries, tool-level attribution, and cost forecast.

Conversational Markdown mindmap workspace: edit complete documents step by step, keep a live right-side visualization synchronized, and open, manage, and export mindmaps from the working directory.

Linux kernel dev domain plugin for DeepSeek Harness (dsh): verification pyramid L1-L4 as model-facing tools + graph-layer governance (anti-Goodhart / blind-spot / patch-conflict) + AGENTS.md contract as a system-prompt section. Plain JS, no build step.

Aseprite-style pixel art studio: the AI draws sprites stroke by stroke with selections, layers, animation frames, gradients, symmetry and reference layers, each step rendered live as ANSI terminal frames.