Plugins

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

OpenBKN business knowledge-network context for DeepSeek Harness

Model attribution panel for the dsh web chat — local, zero-network structural fingerprinting (template token leaks, glitch canaries, tokenizer usage-vector matching) that scores which of 29 AI vendors a session's responses most resemble, with a per-claim evidence ledger and a 12-probe active battery.

Windows toast and a chime whenever a conversation task stops: completed, waiting on your approval or answer, or failed. Clicking the toast reopens that session at your last question, and in DSH Desktop it also raises the window.

Provides a skill for the LinShang LS125 UV irradiance meter and its UVALED-X3 probe: the reverse-engineered 9600 8N1 link (28-byte frames, CRC-16/MODBUS, poll and clear commands), a capture and decode toolchain, and a verified STM32F103 host firmware that reads the probe without the original meter. All code and documentation written by an AI agent (DeepSeek Harness).

The built-in web_search bills a full model turn against DeepSeek's own endpoint; this runs it on an OpenRouter-compatible gateway instead, so search is billed where your chat already is, at the model and price you pick.

A chemistry workbench panel in the DSH web UI. Draw structures on a Ketcher canvas (a script downloads the build; it renders locally in the browser with no backend), then compute on the current molecule with RDKit without calling a model — formula, molecular weight, exact mass, logP, TPSA, hydrogen-bond donors and acceptors, ring counts, Fsp3, stereocentres, Lipinski and Veber rule-by-rule checks, QED, PAINS/BRENK structural alerts and the Murcko scaffold, plus SMARTS substructure matching, fingerprint similarity, format conversion, standardisation and batch clean-up. A retrosynthesis tab talks to a pluggable backend (Retro* by default) over a single JSON-in/JSON-out process, and states what is missing when the backend is not installed instead of inventing a route. The calculations run in this repository's Python package (rdkit), which is installed with pip separately.

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.

Schedule a message into a dsh chat for later: a Schedule button in the message box with a date and time picker, a sidebar panel of pending messages across chats, delivery as a normal user message even with the browser closed, and schedule_message, list_scheduled_messages and cancel_scheduled_message tools so the model can come back to a chat on its own.

Builds, tests, archives and runs an Xcode project or workspace on iOS or macOS through xcodebuild — a live filterable build log, scheme and destination pickers read from the project, and log streaming for simulators and USB devices, including iOS 16 and earlier over libimobiledevice, whose app logs stay readable while the device is locked. macOS only.

A CodeGraph tool scoped to the session's own indexed project, resolved from its workspace directory. One MCP server is launched through npx per project root and shared by every session working there; a project indexed mid-session is enabled without a restart, and the managed child process is reaped when the harness exits.

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.

A dsh-better-sidebar tab that statically parses Qoder Canvas `*.canvas.tsx` files into structured pages in the DSH right sidebar (the source is never executed: no eval, no bundler, no sandbox iframe), with a file-viewer takeover for `.tsx` and a bundled Skill for authoring the format.

Compaction fallback for compaction-basic: when its LLM summary throws, comes back empty or cannot fit the window, the span is compiled deterministically with a seq pointer on every line (vendored dsh-compaction-instant compiler). Adds recall and search tools, /recall and /context commands, an idle trigger at 45% of the window and an on-disk span archive. The engine mounts as one row in the agent preset (docs/dsh-integration.md).

Turns the MacBook keyboard Caps Lock light into an agent status light: on while the agent works, flashing when it waits for your approval or answer, off when idle.

Desktop companion pet in its own always-on-top window: imports Codex pet folders from ~/.codex/pets as-is, with affinity ranks, session-linked activity bubbles, snap-to-edge dragging, a right-click-reachable smart click-through mode and a daily token meter that mirrors the dsh-usage ledger when installed.

Captain-led multi-agent teams that split a goal into tasks and dispatch them along an execution chain to members running in their own sub-sessions, each with its own model.

Plays a voice line or a sound when a turn finishes and a failure cue when a tool call or a turn errors — user aborts stay silent by default and subagent sessions are skipped, both configurable. Three alert modes: voice, effects, or off. Effects is the default and ships 20 built-in sounds (10 alert chimes + 10 nature), each assignable to the done, fail or approval event with per-row preview, so it needs no API key and no audio files; the voice route uses Volcengine TTS with cloned or preset voices, batch-imported voice IDs and fingerprint reuse that skips re-synthesis when text, voice and parameters are unchanged. A third approval slot exists but has no automatic trigger — it only plays when called manually. Playback goes through winmm/waveOut as-is, never changing the system volume or mute state, and the player is spawned detached so session teardown cannot silence it. Windows only.

Feeds every dsh prompt into the local agent-feedback-loop feedback-memory pipeline — captures dissatisfaction, reviews it offline into reflections, and attaches the compiled recurrence-rule context back to the turn, never blocking a prompt. Requires the agent-feedback-loop runtime; running agent-feedback-loop install afterwards wires existing dsh profiles automatically.

SQLite memory entries, a calendar with due-time reminders, and cron-scheduled agent tasks, with 13 model tools and a bilingual zh/en UI.

On-demand memory for DeepSeek Harness: session logs are distilled into layered markdown (a summary, an index and per-topic files), and a mem_query tool returns only the matched entries rather than the whole index. Nothing is injected per turn, there are no dependencies, and every entry keeps a source pointer back to the conversation it came from.

Layered cross-session memory for DSH that pushes only what changed - the first round injects every active entry, later rounds push only added / updated / removed ones, and nothing at all is injected when nothing changed, with keys that merely repeat an entry id left out of the text so the baseline is about 26% smaller. Facts and decisions carry semantic keys (one active truth per key), the model may only write to an inbox that a human promotes, an entry can carry a review date that raises a one-time reminder when due, and search is relevance-ranked with journal lines down-weighted and Chinese matched by bigram. A sidebar tab tells the lifecycle story instead of listing files - entries are grouped by stage (awaiting confirmation / in use / archived) along four axes (topic - one level, human-assigned, type, tag, date), each group can be ticked for batch promote / withdraw / archive / restore / delete / assign topic, and topics can be renamed store-wide or searched on their own. The archived stage reads in three levels - the category says why an entry left (distilled into the docs / useless for good / not needed right now, the first two being defaults you can add to), below it the entry topic stays collapsed until you click it, and entries with no topic sit right under the category. The tab also shows the global and workspace instruction files plus the current injection size. A zero-dependency CLI ships with it, so the store is usable without DSH.

Customize the interface font, size, weight, color and layout from the settings page, Word-style and WYSIWYG, auto-saved. Ships two bundled open-source fonts (STIX2Text, Latin Modern Mono Light) plus an author-recommended typography, and stores settings under ~/.dsh.

Windows system-drive (C:) cleanup for DSH: rule-based scan, five-tier safety grading, a staging area with a rollback ledger, UAC elevation, and migration to another drive — a model tool plus a Web GUI panel.