Plugins

Turn a feature that actually runs into a trustworthy delivery demo video, or a defect into a traceable feedback video: real screen recordings, edge-tts narration with word-clock subtitles, a self-contained ffmpeg pipeline, and a deterministic quality gate (spec, audio, loudness, black/freeze/silence scans) that refuses to pass a fake or broken demo. Feedback episodes add severity/phase chips, a repro-steps overlay and a ticket-ready report bound to the artifact SHA256. Preflight and artifact verification included. Requires Python 3.9+, ffmpeg/ffprobe on PATH, and `pip install edge-tts Pillow`; narration calls the public edge-tts endpoint.

Strips AI-flavor from LLM text with local density scanning and deterministic fact/strength/safety checks; a rewrite that fails verification falls back to the original.

Registers a `dispatch_task` tool that hands scoped or routine work to an isolated subagent, waits for it to finish, then checks the expected files and runs an optional verification command before returning a short report to the main conversation.

Leanary: a mathematical research plugin for DeepSeek Harness, with persistent research workflows and Lean verification.

DSH 探针工具包：卡面合法性、卡契约校验、审计档生成 —— 四个零依赖 CLI ＋ 一个最小宿主插件壳。

Change impact analysis plugin that lifts a code change into an evidence-backed impact and verification plan (CHANGE-IMPACT.md + change-impact.json): affected modules, entry points and public exports, risk levels with factors and confidence, and recommended verification commands (read-only, never runs repository commands). Only read-only git queries (rev-parse, diff, status) are run; suggested verification commands are never executed.

Plain-language trust dashboard for the dsh trust family: aggregates the nine channels (injection interception, write denials, egress blocks, custody-chain verification, tool-surface and prompt drift, leftover scans, forgotten compaction constraints, profile composition) into one right-sidebar panel with a single status light and event cards that translate engine jargon into sentences a non-security user can act on; the read and egress engines run from the package's own npm dependencies so those channels work even without the sibling plugins, and absent plugins simply show as not installed.

Turns what a design, plan or document claims into a model and decides it: UML diagrams rendered, read and reviewed; state machines, protocols and data models checked as models; migrations tested for coverage and rollback symmetry; concurrency claims mined and routed to the checker that can decide them; dependency graphs audited; reports diffed.

By default, blocks marking a team task complete without a passed independent verification record whose commit matches the worktree HEAD, and adds a dependency DAG board and a settings page.

Investment research bundle: 10 tools (search, page fetch, source audit, claim verification, numeric rigor, channel health, workflow loader, chart engine, PDF renderer, PDF gate) and 23 skills adapted from ai-berkshire. Runs a six-phase workflow where four parallel agents (Duan Yongping, Buffett, Munger, Li Lu) research a company, cross-examine each other, and ship a chart-rich PDF with cover, tables, captions and page numbers. Requires Python 3.10+; the chart and PDF tools also need python-docx and matplotlib.

Ship a local DSH plugin project to GitHub and the plugin market in one call: preflight, per-file upload with byte verification, the market registry PR, then pull every published file back and compare bytes.

Multi-model deliberation pipeline for DeepSeek Harness: independent proposals, blind peer review, program-executed evidence verification, immutable revision and independent acceptance on a fresh context.

Signed chain-of-custody for sessions: every watched tool result appends a hash-chained, ed25519-signed record, with commits bound into the chain — tampering with any line or truncating the tail fails deterministic replay verification.

Verified-progress ledger: three tools record a claimed step as progress only after an independent subagent with a fresh context confirms it against the workspace. The declared scope is fingerprinted before and after each verification, so a verifier that changed anything has its verdict voided and the round cannot become progress.

Strict verification for every task: plan 2-7 steps, execute them with worker subagents, verify each deliverable with an independent memoryless verifier subagent, and fix in at most three cycles before reporting honestly.

A mandatory 7-step plan on every request, each step with a binary acceptance criterion, executed through worker subagents and validated by independent memoryless verifier subagents that report PASS or FAIL with evidence.

Keeps a per-turn receipt that later turns do not clear (final todo counts, goal id and phase, end reason, and a fail-closed pass/fail/inconclusive plan verdict), plus a read-only tool to read recent receipts. Stores counts and ids only.

Ships a skill for verifying a change with the cheapest check that still yields a definite answer: an L0-L3 cost ladder from static checks to a single suite, condition polling with a timeout instead of fixed sleeps, assertions that can actually fail, and durations that are measured rather than remembered. The package also carries the two zero-dependency Node tools the skill calls - wait-until.mjs (poll a command, a file, or a port until it is ready) and measure-runtime.mjs (wall-clock timing for any command, plus a segmented timer for library use).

Full edition of the motor-design AI plugin for DeepSeek Harness: adds the L1 (Ansys RMxprt) and L2 (Motor-CAD) precision layers on top of the L0 millisecond-level broad filter, completing an end-to-end chain from requirement parsing to parameter identification, candidate matrix, L0 pre-screening and L1/L2 verification. Mutually exclusive with dsh-motor-ai-l0 (uninstall l0 first); the shared core @wangxue98/dsh-motor-ai-core installs automatically. L1 needs Ansys AEDT (RMxprt) and L2 needs Motor-CAD installed locally. Distributed under the PolyForm Noncommercial licence; L1/L2 require an activation code. Telemetry is on by default: per-tool usage counts and design-experience samples that the author describes as desensitized are sent to the author's server at wangxuewangxue98.deno.net, and fault assistance can upload fault reports; switch them off with telemetryEnabled, designExperienceUpload and faultAssistEnabled in the plugin config.

Ports the obra/superpowers methodology as 14 native DSH skills — brainstorming, writing-plans, executing-plans, subagent-driven development, test-driven development, systematic debugging, parallel agent dispatch, git worktrees, code review, verification before completion and skill authoring — served through the DSH skills registry with their scripts, references and cross-links intact (frontmatter folded into a manifest, prefixes realigned to DSH skill names). Requires DSH session format v4 (official DeepSeek Harness 0.1.7+): the /superpowers slash command declares the producer-owned source kind plugin:dsh-plugin-superpowers.

Runs Superpowers as an agent preset and gives each skill its own subagent model from a Settings table, so TDD, debugging and verification no longer all inherit the parent model.

Verifiable authorization, execution evidence, and offline delivery verification for DeepSeek Harness

Deterministic Reasoning Engine (DRE) for dsh: dre__* tools for knowledge verification (three-stage discrimination), deterministic cognition loops, constraint solving, mental models and synapse memory - strengthens information certainty.

Linux X11 computer use for DeepSeek Harness: 9 tools (screenshot, move/click/drag/scroll mouse, type, key combos) driven by a zero-dependency Python XTest helper — native-pixel coordinates, per-action verification, optional auto-observation screenshot.