Plugins

Adiciona ferramentas de status, diff, log, commit, branch e checkpoint opcional do Git, todas condicionadas a aprovação

Perfis de prompt reutilizáveis em Markdown para o DeepSeek Harness, com seleção de modelo por turno, substituição de argumentos e restauração de estado

Ferramentas somente leitura de informações do dispositivo Windows: uma ferramenta de agente por categoria de dispositivo Win32 (hora, sistema, cpu, memória, disco, gpu, rede, bateria, processos, usb, áudio, impressoras) via coletores WMI/CIM e Node os

Auditoria somente leitura de higiene de credenciais para frotas de agentes: permissões de arquivos de credenciais, credenciais embutidas em remotes do git (mascaradas na saída) e contagem literal de tokens de provedores; sem dependências e determinística

Recuperação leve de contexto sob demanda: ferramentas context_query / context_slice / context_grep que leem o histórico já persistido de volta, com citações seguras para replay

Deterministic session evidence reports for DeepSeek Harness: /transcript writes styled single-file HTML / Markdown / JSON reports from canonical session logs, /stats prints a terminal stats card, /archive writes per-session ZIPs

Persistent personal todos shared across DeepSeek Harness sessions and projects: SQLite storage, Agent tools, a native sidebar and turn-tail cards, with user-managed workflows or optional dispatch of individual todos to Agent sessions.

Windows-native computer use for DeepSeek Harness: two tools drive and read any desktop app. One batch call runs find, click, type, key, read, wait and screenshot steps in a single engine pass, so a task whose steps are known up front costs one model round trip; reading returns window text rather than an image, and input and capture prefer UI Automation patterns, Win32 messages and offscreen PrintWindow so the user's focus and pointer stay untouched.

Render and iterate on Blender scenes from DSH: 16 tools for scene specs, previews, visual review and delivery renders, with immutable revisions and an approval gate.

Fronts stdio MCP servers with three router tools (list_capabilities, describe_tool, call_tool) so schemas load on demand instead of riding every request; shapes every tool result through a deterministic output ladder that archives the original first (retrieve_spill reads it back); prices tool groups in tokens and can hide built-in groups per agent. Bridges to a standard-library Python router, so Python 3.9+ is required.

Mounts the mcptoon MCP gateway as one stdio server, so the agent discovers the tools of every MCP server you have configured through mcptoon's compressed view instead of full JSON schemas on each turn. Ships a doctor CLI that checks the mcptoon executable resolves and prints the exact command/args override when it does not.

Edit global and project instruction files in DeepSeek Harness settings, with project-chain discovery, byte-budget display, and save-conflict handling.

Pre-execution safety valve for DSH that judges with TypeSafe Jev: it hooks tools/pre-execute and decides every bash/pwsh call by first applying offline static rules, then by asking the Jev model — the System One model from TypeSafe, which returns a structured decision instead of prose — one yes-no question ("will this command irreversibly delete or overwrite real data?"), turning the answer into allow, revise, block or escalate; revise hands the model a safer rewrite, escalate offers a one-shot human token; exhausted credit or a missing API key degrades loudly instead of failing silent, and a missing key is requested in the conversation itself (`guard key set`, read from stdin); every verdict is appended to a shared audit log and the text people read is bilingual zh-CN/en.

Compaction fallback for compaction-basic: when its LLM summary throws, comes back empty or cannot fit the window, the span is compiled deterministically with a seq pointer on every line (vendored dsh-compaction-instant compiler). Adds recall and search tools, /recall and /context commands, an idle trigger at 45% of the window and an on-disk span archive. The engine mounts as one row in the agent preset (docs/dsh-integration.md).

Session health check for DSH, read-only: scans the whole session library (totals, largest sessions, warnings for oversized sessions and event-count blowups) and deep-inspects a single session log (tail-balance / crash-tail check, tool-call/result pairing, event-type distribution).

Create and configure Agent presets from a single settings section — persona prompt, a checked knowledge-base entry list injected into the system prompt, individual switches for four knowledge-base tools, per-Agent narrowing of MCP connections, and batch knowledge-base import.

Model switching and reasoning-effort control for DeepSeek Harness: set_model and list_models agent tools let the agent autonomously change its provider, model or thinking depth (reasoning effort) mid-task with a mandatory reason, a provider whitelist and a context-window token-pressure guard, the active model is injected into the runtime context, and Plan Mode auto-transition switches to a configured planning model on entering plan mode and restores the previous execution model on exit.

Long-form novel writing plugin: each book is a git repository of frontmatter files, with 39 DSH domain tools and a web writing UI. Deep import drafts candidates, AI adoption into canonical assets requires DSH approval, and deterministic continuity checks ship with a report-only benchmark. Independent open source (MIT), not an official DeepSeek product; requires Node >= 24.11.0 and currently targets DSH 0.1.2-rc.1.

Registers any set of HTTP APIs as paired doc-query and request tools for the agent.

9router-backed web search + fetch providers for DeepSeek Harness (ctx.web). Wires the native web_search/web_fetch tools to 9router's /v1/search and /v1/web/fetch endpoints.

Approval-free writes into whitelisted directories — wraps the filesystem fence for write/edit tools and auto-answers bash sandbox escalations that touch whitelisted paths, with a settings GUI.

Keeps a redundant sandbox-escalation argument from failing a tool call. Escalating tools (pwsh, bash, write, edit) advertise the full sandbox_permissions enum, but DSH only accepts a level strictly wider than the one already in effect — a check its own source calls 'deliberately not a schema constraint'. A model that reflexively passes the argument therefore picks the level it is already at and the call dies before running with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "workspace-write" mode', costing some models a whole turn of retries. This plugin registers one tools/execute waterfall listener and, only on that documented rejection and only when the arguments really carried an escalation field, re-issues the identical call once without it. Safe by DSH's own documentation: the rejection precedes any execution ('nothing has run'), and the corrected call cannot match again, so the retry is loop-free. Reproduced and verified end to end — before: isError true, the command never ran; after: the command's real output, isError false, one tool/call and one tool/result. Zero dependencies.

Native DSH right-sidebar tab that lists the ports this machine is listening on together with the process behind each one, and offers per-port actions to open it, copy its address, reveal its working directory or end the process.

Manage Proxmox VE through conversation: 116 read + 116 write tools covering VMs, containers, storage, nodes, clusters, backups and firewalls, with API-token or username/password (ticket) auth.