Plugins

Four read-only tools over a WeKnora knowledge base: list knowledge bases, hybrid passage search, reassemble one document's chunks in order, and WeKnora's own cited RAG or ReAct-agent answer with a resumable session id.

WeKnora knowledge retrieval tools for DeepSeek Harness (dsh): semantic search, document reading and RAG/agent answers over your own knowledge bases.

Config-only bundle that mounts Ouroboros through the DSH MCP client, exposing 36 interview, Seed, execution, evaluation, and evolution workflow tools in DSH.

Single-bundle reverse-engineering and pentest security plugin: first-turn tool narrowing, domain routing, and 33 tools covering APK, web, native binary, protocol, malware and LLM samples — with unpacking, license-bypass and anti-analysis case playbooks, an H-CoT evaluation engine (semantic routing, /hcot command), a web workbench with a ledger-driven tool shelf, an on-disk case workflow (auto-persisted evidence chain, E-numbered validated findings, post-compaction resume), GitHub-based external tool discovery, and 361 on-demand reference docs.

Quantitative R&D toolkit for DeepSeek Harness — 59 tools across six domains covering market data, indicators, factor evaluation, walk-forward ML validation, risk (VaR/CVaR/drawdown/Beta with Kupiec POF), options, bonds, FICC and fund simulation, with an end-to-end PDAT→PET research pipeline.

Controls your real Chrome from DSH over a local WebSocket bridge: tab management, navigation, DOM snapshots, page JS evaluation, clicks, typing, screenshots, waits and dialog handling behind a Settings toggle.

Local-first A-share research workbench for DeepSeek Harness: market dashboards, watchlists, valuation, four investor agents, versioned reports, and continuous post-report chat.

Host-side DSH evaluation control plugin: injects one evaluation trial's variables, budget limits, session root and fork lineage into the agent process, routes its model calls through a host broker under a gateway lease, and writes a schema-versioned bundle descriptor for evidence attribution.

OMK — Observe. Measure. Know. Evidence-backed knowledge changes for AI applications.

Evaluation harness for DSH plugins: YAML cases drive real headless agent runs, assert on tool calls, args, results and token usage, with a baseline gate for CI regression.

Evidence-first self-evolution controller: bounded Cordis candidate generation, one-shot real-Loader admission, Harbor evaluation, and a crash-resumable journaled lineage.

Drives a locally installed Moli headless browser from DeepSeek Harness: rendered fetch, JavaScript evaluation, Markdown, semantic trees, screenshots and PDFs. A CSS selector returns one container rather than the whole page (measured 40-80x fewer tokens on listing pages) and scroll triggers lazy loading. Installs Moli when it is missing; verified with a real engine on Windows, Linux and macOS.

Finance data toolkit for DSH agents: number and currency formatting (incl. Chinese wan/yi units), return and CAGR math, valuation and profitability ratios, PV/FV, risk metrics, and a data-quality checklist.

Proactive multi-model scheduling plugin: multi-source signal intake with dedup and urgency ranking, a four-way execute/defer/dismiss/ask-user decision engine, DAG plan generation with parallel model execution, quality reflection with automatic retry and model switch, long-term memory for task patterns and lessons, and strategy evolution via genetic algorithms with sandboxed evaluation and canary rollout.

Runs 3 or 5 coding-agent candidates in detached Git worktrees, validates their patches with project commands, ranks only passing candidates, and requires separate approval before applying the winner.

China A-share stock research: ticker search, announcements over any date range, financial report cards, valuation profiles and signal-factor explanations (~5,000 stocks since 2011, public read-only data service), plus a link-out tool to an external trading-sandbox product.

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

PR evaluation and improvement consultant: assesses PR success probability based on historical anti-patterns and success patterns, with one-click scoring and actionable suggestions.

Automated daily content pipeline for Insta360 GO 3S: BLE/WiFi remote capture of aquarium footage, wireless import, ffmpeg quality evaluation with decision log, Auto editing (segment selection, TTS narration, music, subtitles), and Bilibili upload via biliup (dry-run by default).

Insurance actuary — runs real actuarial calculations (life & P&C reserve valuation under C-ROSS II BEL+RM, profit testing NBV/VNB/IRR, embedded value EV, pricing & loss-triangle reserving), not just explanations.

Runs reproducible DSH profile and patch experiments with guided case authoring, assertions, Web comparison reports, recovery, and policy gates.

A model-native meta-agent plugin for DeepSeek Harness: the model synthesizes task-specific workflows at runtime from five agentic workflow patterns (prompt chaining, parallel workers, router, supervisor, evaluation loop) and coordinates tools and subagent

Evaluation guard for DSH: workspace-only filesystem, no network/subagents, wall-clock limits, and task installation for meow-ai-arena and benchmark tasks.

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.