Plugins

DeepSeek Harness plugin that wraps @stardeckai/lgtm — a Jev-powered linter for tests that pass but prove nothing. Ships the CLI as a dependency, reuses the TypeSafe credential stored in DSH, and exposes lgtm_audit / lgtm_status to the agent.

Read-only side branch in the right sidebar: quote text to ask follow-ups without polluting the model context of the main session; every follow-up rebuilds the branch from the latest settled turns of the main session, and writes are refused at the tool-execution layer so the prompt prefix stays cacheable.

Replaces the DSH sidebar with a fixed 2×4 board of eight standing agent seats; each seat shows its own status, latest tool call, reasoning and result, and a settings switch restores the stock sidebar at any time.

DSH plugin that registers the ai-eight-honors-eight-shames skill: eight checkable working rules for coding agents (verify before calling, confirm ambiguity, cite evidence, reuse before creating, test before claiming done, follow local conventions, separate fact from inference, keep changes reversible) plus a ninth rule that logs each user request and the change made in two fixed report files at the workspace root.

0.8.6 fixes a startup crash: the host runtime package is an optional peer, never an installed dependency. TypeSafe Jev (System One decision model) wired end to end into DeepSeek Harness (0.8.6). Seven tools: jev_decision (1-25 parallel atomic verdicts in one call; noul/choice/score; typed answers with calibrated confidence; measured median 266-484 ms; verdicts only, never prose), jev_choose (rank 2-10 candidate approaches - fit 0-3 and risk - into an explicit composite with a recommended pick), jev_batch (NEW in 0.8.6: one set of 1-5 judgments over 1-20 texts, one real call per text at bounded concurrency, returning a paste-ready markdown table sortable by a judged dimension; built-in sentiment/priority/intent/pii/spam presets; a failed row is reported as failed with the raw error, never guessed), jev_usage (locally measured usage: calls, tokens, estimated cost, latency median and p95, per-tool mix, rolling windows, projected burn rate, optional local hard budgets, and a declared-balance remainder), jev_overview (session ledger), jev_guard_status (guard counters plus a registrations block that surfaces per-surface registration failures) and jev_verify (frozen 27-question live benchmark at concurrency 6: 96.3%, 26/27). WHAT IS NEW IN 0.8.6 - the ledger survives a restart, the remainder is derived instead of invented, and the plugin can now do batch paperwork. (1) The local ledger persists to $DSH_HOME/jev-usage.json BY DEFAULT, so the cumulative total no longer resets when the host restarts. Two real bugs behind the old silent zero were found and fixed: the ledger path only honoured DSH_HOME (absent inside the host process, so persistence was silently disabled and the file name was null), and save() wrote the still-empty in-memory ring over the history file because it ran before the first load while the debounce window swallowed the follow-up write. (2) Remaining is derived, never invented: TypeSafe exposes no balance endpoint - /v1/usage, /v1/quota, /v1/account, /v1/account/balance, /v1/balance, /v1/credits, /v1/billing, /v1/me, /v1/limits and a dozen more all return 404, and only /v1/models answers, with no balance headers - so the panel shows the remainder as your declared balance (quota.declaredBalanceUsd) minus locally measured spend since quota.balanceSince, and says plainly that it cannot be fetched instead of printing a number. (3) The composer pill re-reads every 20 s instead of every 60 s, so a call you just made shows up while you are still looking at it. (4) The collapsed pill leads with the remainder once you declare a balance, and the cumulative row is renamed when the ledger is on disk. Every tool has an in-conversation structured view; the Settings > Plugins card covers credentials, tool switches, the auto-guard, the dashboard, the prompt section, usage/quota and auto-triage. Honest by design: no API key means an explicit error, never fabricated results; every registration is quarantined so a failure degrades one surface. Tests 38/38 (npm test, ~2.5 s). Client half applies on refresh; server half needs a host restart.

Ren'Py galgame production workbench: a host-side project service (write gateway plus git snapshots, a dialogue/scene dialect parser, derived progress, human-only review stamps, pinned-SDK validation and playtest, local publish) behind one seam, driven by an embedded web panel and agent tools.

DSH Plugin DevKit: runtime observation kernel, isolated debug boot, host contract tests, slot preview

Model channel manager: several provider/model candidates share one virtual route (roundrobin/<group>) with failover, retry, timeout and cooldown; a settings tab edits providers and groups, runs per-model speed tests and real single-model request tests, and a seven-day health panel aggregates latency, failures and upstream token usage (input, output, cache and reasoning).

Compares existing DSH sessions or runs controlled A/B trials between agent presets, showing aligned timelines, paired metric deltas, explicit success checks, and exportable reports.

Combines fault knowledge-base symptom-to-cause rules with similar past cases to rank candidate motor diagnoses with evidence terms and suggested extra tests.

Fullscreen business-app framework for DeepSeek Harness Web with a dark-sidebar workbench bundling a database connectivity tester and SQL query panel, a two-level knowledge base (bill and accounting) with local search and Word document ingestion, metadata environment comparison with alter-SQL generation, a data dictionary, agent log-search report demos, a system test-case runner, Evernote-style notes, developer utilities, and mini-games.

Scans the whole C drive and classifies every large folder into A/B/C/D/E/P (safe cache / relocatable / junction-movable / abandoned software / config-memory redline / personal files), then deletes, moves, or redirects on demand — with strong redline protection, dry-run preview and undo. Unknown software decided by LLM fallback + human confirmation. Works on DeepSeek Harness 0.1.7 through 0.2.x, tested on 0.2.0-rc.1.

DeepSeek Harness (Cordis) plugin — bi-temporal VSA memory + cognition engine + BLAKE3 provenance, exposed as a DSH storage+session plugin. End-to-end tested with a real Python subprocess.

Conversation-level multi-agent workbench for editable task planning, real child-session observation, plan-versus-runtime comparison, and evidence-backed recovery previews; tested with DSH 0.1.1-rc.2.

Runs a parallel code review squad of read-only reviewer subagents (security, correctness, tests, style), each optionally on its own model, and aggregates one severity-grouped report from /review or a code_review tool call.

Uses a GitHub App to report open PRs and the latest Actions run for the current repo without returning secrets.

Parses DSH session logs to attribute AI-written files, overlays c8 coverage, and reports AI vs human code coverage with a trust score, plus a check/fix/verify tool loop for closing test gaps.

Stavros RedTeam for DeepSeek Harness (DSH) — authorized red-team persona + scope-guarded pentest tooling (persona, 24 subagents, methodology and 78 zero-dependency guard tools).

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.

Triggers GitHub Actions workflows and local test pipelines, streams their logs back, and on failure hands the log tail to the agent for diagnosis.

DeepSeek Harness (dsh) plugin for @tabilo/ai-code-review: registers the ai_code_review tool (review | context) that reuses the Node.js engine to collect diffs, run tests/coverage, do impact analysis, and feed pack skills to the model.

Load testing with Grafana k6: smoke-test first, then run scripts and read percentiles from the JSON summary.

Enhanced SSH ops: connectivity testing, remote ls, ssh-config import, known_hosts fingerprint checks and multi-host exec.

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.