Plugins

One leader, many sessions: tell the leader the goal and it splits the work into cards, runs persistent worker sessions in the background, collects their reports, and keeps the facts on a per-project board in the right sidebar, so several features move in parallel instead of one at a time. Project-level LEADER.md and SLOTS.md prompts shape every request, and `read_worker_session` replays a worker transcript read-only without waking it.

Multi-round deep research in the DSH sidebar: each round fans sub-questions out to parallel sub-agents, then continues from where the last round stopped and writes a cited report.

Multi-agent agent team of employee AI subagents for DeepSeek Harness — dsh-company: employee management, CEO bidding, n8n workflow orchestration, drag and drop canvas. DeepSeek Harness plugin with seven built-in roles (project director, product manager, tech lead, engineer, data analyst, QA, reviewer), each with its own persona, model and tool whitelist. Broadcast a mission and the employees bid for it themselves — the first line of their answer must be 【accept】 or 【decline】 — so accepted work runs in parallel instead of down a pipeline. The workflow canvas wires employee nodes with the start node, references each upstream result with {{input}}, and runs the graph in topological layers: parallel across employees, serial per employee, downstream skipped when upstream fails. Ships a web panel for the employee management tab, the mission board and each employee's transcript, the /dsh-company slash command, a live mirror into the built-in agent-team panel, deletable missions, and a private memory directory per employee.

Native generation-time Mixture-of-Agents: every turn, reference models run the same session context in parallel as pre-run drafts and one aggregator executes with full tooling; config-as-model recipes, F mirror / R trimmed views, enforced subagent gating (dual-shape session indexing), derived per-recipe vision (vision refs relay image reads to text-only aggregators), tiered cadence with separate steering and patrol rosters plus frozen reuse between beats, degeneration guard dropping degenerate reference output, anonymized model face (failure notices carry no provider identity), and cache-friendly guidance placement (the rehearsal record is pinned where it was produced instead of appended to every request, so the cached prefix covers it and each step pays only for what was added since - on by default across every cadence).

Adds a comet-like light band that flows along the window edge of DeepSeek Harness — up to four in parallel, colored by each session's model, reversing direction while waiting for your reply, and returning to the composer or the workspace once the conversation ends.

Runs a second agent: hands independent subtasks to a local Codex CLI in parallel (up to three at a time), and asks it to review a design or a plan before the user sees it, returning conclusion, evidence, counterexamples and a verification step. A dispatch missing its timeout or its acceptance check is rejected by the plugin, not by the model remembering to check.

Saves architecture and validated plans, runs native AgentTeams workers with approval, parallel coding and independent review, and summarizes progress and verification results.

Web search and fetch provider for DeepSeek Harness and Pi: anonymous-first routing across Exa, Tavily, Parallel, Firecrawl and TinyFish, with opt-in billing, quota preflight and bounded cancellation.

Cross-session coordination for DeepSeek Harness that lists parallel sessions, relays messages with sender attribution between them, and pauses or resumes a session when task phases conflict.

Role-based expert subagents for DeepSeek Harness with a task sidebar: explorer, librarian, oracle, designer and fixer delegate in parallel, each with its own model and reasoning depth.

Agent preset: one session runs a three-phase auto-development pipeline — interactive design with parallel research subagents, goal-driven development with reviewer/developer subagents and per-package budget ledgers, then an acceptance fix loop.

Extreme LLM-call compression for DeepSeek Harness: title short-circuit, in-flight dedup, 24h replay cache, and batch-merging N parallel requests into 1 upstream call via a `[[TASK n]]`/`[[ANSWER n]]` delimiter protocol - fewer API calls, less spend, same answers.

Round-table meetings for DeepSeek Harness 0.2.0-rc.2 on Windows desktop, reusing existing Agent sessions with discussion, editable task cards, sequential and parallel steps, shared meeting files, and secretary minutes.

Enhanced desktop shell for DSH: auto-starts the local backend on launch (no browser tab), asks before closing the backend on quit, and starts the backend in parallel with Electron for faster cold start. Fork of dsh-clean-desktop-shell.

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.

Launches a fresh, continuable parallel session from the composer command menu (/side-chat) while the main session keeps running.

Shows a 0-100 conversation coherence badge and commentary by running parallel contradiction analysis on the live DSH session, with a manual trigger and interval-based auto-analysis (on by default, editable per session or globally).

Per-provider concurrency gate on the llm/stream waterfall: holds surplus model requests in a FIFO queue inside DSH so main agent, subagents and compaction take turns on a single-slot local server (llama.cpp --parallel 1) instead of timing out; maxConcurrent / maxQueued / queueTimeoutMs.

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.

Contract-drafting agent preset: 11-stage lawyer workflow with 5-way parallel AI review, decision gates, and domain packs for general, employment and equity-investment contracts.

Declarative DAG runtime for DSH tool plans with bounded parallel execution, read-only retries, per-step checkpoints, cancellation, and conservative crash recovery.

Logic-risk review before rewriting: audit the source, decide each fix, generate several drafts in parallel, and export with a per-draft audit report. Bring your own OpenAI-compatible API endpoint and key - the plugin ships no model and returns 403 until one is configured.

One leader, many sessions: tell the leader the goal and it splits the work into cards, runs persistent worker sessions in the background, collects their reports, and keeps the facts on a per-project board in the right sidebar, so several features move in parallel instead of one at a time. Project-level LEADER.md and SLOTS.md prompts shape every request, and `read_worker_session` replays a worker transcript read-only without waking it.

Skill bundle that installs the codex-collab skill for driving the local OpenAI Codex CLI as a vendor instead of a consultant: every delegation carries acceptance criteria and a self-test script, the result is verified by running those tests locally, and a failure is handed back with its original error output; batch delegation runs sequentially (parallel subprocesses are not usable locally) and multi-turn continuation stays inside one session. Requires the local Codex CLI and PowerShell 7+; the helper scripts are Windows-native and only partially work on macOS/Linux.