Plugins

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

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

Guides RTL design and verification in DeepSeek Harness, with project scaffolding, evidence checks, and OpenROAD/ORFS setup.

Keeps code edits in a review loop instead of letting the model edit files: each change is proposed as a two-column diff card with line numbers, applied by hand or with one click, and handed back for verification with another click.

Socratic tutor tools for DSH: cited retrieval, page images, chapter index, session review, embedded console. Teaching behaviour lives in dsh-socratic-persona.

Public-username checks over a pinned 481-site Sherlock manifest; six states, random negative-sample verification for claimed results, default core 41, all capped at 120, NSFW off by default.

Keyword-rule scan of a project directory for tax-industry compliance gaps ahead of regulatory audits: accounting voucher and ledger retention set under 30 years, invoice-title lines with no taxpayer ID, tax data leaving China with no security assessment or standard contract mentioned, and e-invoice lines with no verification or de-duplication mentioned, with rule sources kept in rules/.

E-commerce order analysis skill for DSH: refund-type classification, return-rate statistics, interception and refund-abuse loss accounting, after-sales analysis with product warnings, delivered as a single Excel workbook with a per-order detail sheet and a sampling verification sheet (the agent builds it with Python: pandas, openpyxl, matplotlib).

Registry of 119 quant and crypto sources covering regulator filings, point-in-time fundamentals, macro series, exchange APIs and on-chain data, each tagged with an authority tier, verification state, five-state point-in-time, revision risk and dataset tags; ships qt_source_find and qt_source_audit tools for source lookup and for citation audits that redact credential-like URL parameters.

Measured /pua for DeepSeek Harness: every pressure message gets a receipt comparing the last N completed model steps with the next N — tool calls, verification-class steps, repeated-call peak, failed calls and text volume — with a three-way verdict (changed approach / merely restated / no change) and a daily ranking of which sentence moved the work. Ships a conversation-view panel, a /pua command with list/status/receipts/rank/off, append-only local JSONL receipts (no tool arguments, content or session ids), 38 node:test tests and a zero-dependency build. Reports observed differences, not causality. Inspired by MichengAI/dsh-pua (independent code); it registers the same /pua command, so it cannot be installed alongside dsh-pua.

Session bus for DSH: independent sessions in one project message each other by session id or registered name and wake the target, with a sidebar inbox, unread badges, a roster verification tool, and a per-project switch that stays off until .dsh-bus.json opts in.

Appends one short user message before the next step when the model is circling: the same absolute path written three times, the same normalised tool error returned twice, or two steps since the last write with neither a verify nor a search. Verification is recognised from four tool names (`ops_bash`, `lsp_diagnostics`, `verify`, `run_tests`), searching from eight. Each signal fires once per turn and only after a new write or error, is silenced for the whole turn when you say not to search, and is skipped in subagent sessions. Ships the `stuck-gate` skill at bundled rank 600, so a user-level copy at rank 400 overrides its wording without touching code, plus a read-only gain panel at `/better-debug` that counts firings, sessions covered and whether the next tool call changed class; it does not estimate tokens saved.

Long-form manuscript verification team for DSH: installs 10 skills that run a read-only content/structure check, three-tier revision proposals, a human-selection gate, exact replacements and a final re-check; it never edits the manuscript by itself and requires Agent Teams to spawn teammates.

Requirement-to-evidence audit for DSH sessions: maps each requirement to tool calls, files and commands, records per-requirement verification, and sends missing items back to the agent.

Serves this harness instance's Web GUI on a fixed port with device pairing and Cloudflare Access verification.

DeepSeek Harness 插件：把对话整理成论文。按说话人还原上下文、提炼带出处的论点、生成论文骨架，并用 Crossref/DataCite/OpenAlex/arXiv 逐条核验引用。

Electricity activity ingest, location-based GHG calculation, row verification, workpaper and partial ESRS pack.

Runs project check commands itself and records the real exit codes, pins the result to a git or file workspace fingerprint, expires the evidence when the tree changes, and reminds the agent to verify before claiming completion.

Runs an approved OpenSpec change to completion while the model stays a mechanical forwarder: a bundled Python CLI computes the ticket DAG frontier, claims tasks atomically, prepares one git worktree per assignment, and returns exact actions. The session delegates each action with the DSH subagent tool and reconciles the completion notice against a hash-bound receipt produced by re-running verification commands on a clean, advanced HEAD, so free-text "done" never counts. Runtime scope changes are plain tasks.md edits. Liveness is observable, not guessed: status returns a relay block (elapsed and lease budget, receipt presence, heartbeat and activity age, a suggested action); abandoning a plausibly-still-working attempt is refused with the judgment data unless --force; a late sealed receipt is revived by adopt after full re-verification instead of rebuilding the ticket; dispatched subagents refresh a progress heartbeat outside the worktree. Requires Python 3.10+ on PATH and a git project that uses OpenSpec.

AI-native SDLC as a DeepSeek Harness bundle: task state machine and artifact chain, independent verification with structured verdicts, per-issue rework and re-verification, test freezing, RSI retrospectives, and a read-only dashboard.

Rclone backup tooling with four tools: target inventory, local/remote status, rclone check verification, and approved copy/sync transfers with dry-run previews and an audit line. Requires rclone installed and a remote configured with `rclone config`; the plugin never reads the rclone config or credentials.

Community fork of kingcharleslzy-ai/dsh-purge (do not install both - both register the same `dsh-purge` row as the `dsh-purge-community` package): the community '破甲' (unrestricted-mode) control for DeepSeek Harness - host-policy patches, prompt and rule settings, diagnostics, verified updates, and local backup and rollback, plus a three-layer bootstrap installer (engine, code and prompt layers) with its own verification pass.

Delivery workflow preset for DeepSeek Harness: an agent protocol plus seven tools that keep user requests verbatim, record feedback decisions, plan tasks with acceptance criteria, log real verification commands and exit codes, and write completion summaries as per-project JSONL files.

Serves the OwlCoda RunKit skill in the DSH skill catalog: project-owned objectives, work items, candidate identity, verification receipts, handoffs and recovery stay in project artifacts. Installs instructions only; the project-local owlrunkit CLI is a separate setup step.