Plugins

Project-level memory built around a ledger whose structure the AI designs per project; the plugin only handles detection, injection, write-back, archiving and git. Memories are split by meaning: the active ledger holds current state, the turn journal is append-only, and decisions, the goal tree and lessons are one-card-per-file (with a multi-dimension index over the card folders); the fundamental principles file can be changed only by the user. There is a single compaction mode: before compacting, the AI sorts the work into three buckets - what must stay in context and is re-injected verbatim, what is written to the project's _stash/ for later lookup, and what is dropped. When a conversation is opened in a container workspace holding several projects, it can be locked to one sub-project (the lock lives in the plugin's own home and survives restarts; it leaves no marker in your project). Also an activity log with five levels, where L4 stores the user's own words verbatim (never injected, queryable on demand). Before each compaction a verbatim capsule (user quotes, raw errors, changed files) is written to disk, and both the capsule and its source material survive a restart; a handoff document lets a new conversation resume the previous one. 21 tools, 12 subcommands, 39 settings (one of them switches whether the settings panel or each project's manifest wins). Runs locally, no runtime dependencies.

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

Run one instruction on every online Windows and macOS machine, across networks and regions: a dependency-free relay talks to each machine over outbound connections only (Tailscale, a public VPS behind TLS, or a tunnel), every machine runs the command in its own checkout, and results come back with a commit, a working-tree fingerprint and a command hash so an environment mismatch is reported as unverifiable instead of being mistaken for a different result. Sending work needs its own operator token, separate from the per-machine device token.

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).

OpenCode GO quota widget pinned to the sidebar, with rolling/weekly/monthly usage bars, an elapsed-versus-remaining time bar under each, a same-origin usage proxy, an /opencode-go command, and the runtime x-opencode-session fix for GO gateway chat requests. Fork of yumusb/dsh-opencode-go-usage.

Adds an Explain button to the approval card: one model call returns exactly three lines reading the pending operation, covering what it does, which files or system state it reads, writes, modifies or executes, and a risky/attention/safe verdict with a one-sentence justification. It also renders the detail area for `write` and `edit` calls, which the shipped renderer leaves blank because it only reads a `command` field.

Maintained fork of dsh-approval-gate. A neutral operation whose confirmation count has reached the threshold auto-approves when the judge is unavailable, instead of prompting a human again; approver-facing explanations are generated in Chinese from the real sandbox mode, command and paths. Also carries deterministic hard-deny for credential exfiltration and system-path destruction, judge-input redaction, a judge model candidate chain, fingerprint-scoped allow rules, and an approval view with unified diff and one-click revert.

Runs DSH's stock bash tool on Git Bash for Windows, so commands go straight to bash -c instead of being re-parsed by the pwsh tool.

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.

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).

Runs a thesis-antithesis-seal debate whose verdict is computed from real command exit codes and case counts, never from agent prose.

Unofficial DeepSeek Harness settings panel for Command Code: credits, usage windows, and model-catalog sync.

Read-only DeepSeek Harness Web sidebar version chip that shows the running DSH version, npm latest/next/alpha channels, compatibility labels, and a copy-only upgrade command.

Direct web search button and /search slash command plugin for DeepSeek Harness.

OMC-style multi-agent orchestration for DeepSeek Harness: 29 omd-* skills and 12 /omd-* slash commands over the plan-execute-review-verify pipeline and team/autopilot/ralph modes.

Chinese-first UI enhancement: translates slash-command names and plugin-inventory cards with three display modes (Chinese only / Chinese + English / off), switching instantly without losing English.

Adds a /dshpp slash command that reports session and token usage, cache-hit rate, and estimated cost from harness session logs; the repo also ships a CLI and local web console for lifecycle, provider, session, and plugin-security management.

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.

Registers a /code-review slash command with five parallel review lenses and per-finding confidence scoring, for both pull requests and local code.

Daoist Canon (DaoZang) retrieval skill: keyword or semantic search over 285,117 scripture chunks with exact original-text extraction (line numbers, hit markers), and one-command workspace setup from the Godners/DaoZang dataset.

Decision-and-goal memory with lineage: explicit commands and a model tool record decisions deterministically, a status card re-anchors them across compaction, a lossless event stream with BM25+jieba retrieval backs it, and a scenario-level fidelity regression suite gates releases.

Layered long-term memory MCP server: raw turns → task fragments → daily summaries → topic indexes, local MiniLM 384-dim embeddings or OpenAI-compatible API backend, semantic + Jaccard-fallback search, one-command DSH plugin install.

IDE-style run configurations for DSH: save LLM prompts and shell commands as reusable run configs (global or per-workspace), run them from the session header or the new-session page, and manage them via the task_run_config tool with approval-gated writes.

QQ official bot (q.qq.com) integration for DeepSeek Harness: chat with the full agent from private chats, groups and channels — WS long connection (heartbeat / reconnect / RESUME), per-chat session isolation, standard agent preset, approval inline buttons with /revoke, slash commands, whitelist fail-closed, credentials via the credentials domain.