플러그인

DeepSeek Harness의 대화별 총 토큰 안전 퓨즈: 각 AI 대화에 토큰 퓨즈를 달아 사용자 메시지마다 독립적인 총 예산을 설정하고 입력, 캐시, 사고, 답변을 일괄 제한합니다. whale 슬라이더를 제공하며 다음 사용자 메시지에서 자동으로 초기화됩니다.

See what a conversation feeds the model, what your rules keep out, and what one click would change.

Adds an AIignore tab to the right sidebar: scores the open conversation and its folder across five dimensions, blocks reads of build output, lockfiles and logs before they reach the model, and writes the .aiignore rules for them one button at a time.

Deep PTC mode is an open-source agent preset for DeepSeek Harness that keeps the built-in PTC tool surface and replaces the persona with a working contract: a DeepSeek identity and unlimited-token-budget instruction so the model does not skip reads, commands or checks to save tokens; planning by estimated size (internal up to 5 minutes, shown without approval up to 20, approval required beyond); and asking about unclear intent instead of guessing. Waiting is limited in code by wrapping the official shell, job and question tools: foreground commands move to background jobs after 30 s (configurable), a steered user message ends the current wait so the model reads it, foreground pauses over 5 s and long timers in run_code are refused, and questions run in timed mode. A settings card selects the preset executor — Automatic, WSL Bash, Windows PowerShell, native Zsh or native Bash.

Session-scoped checklists the agent maintains, with a tree per session, a token-budgeted prompt digest and a right-sidebar tab where item titles can be edited.

Beyond the built-in @: line ranges (@src/a.ts:12-40), skills, plugins and any git repo — with the token cost of each reference shown before you send.

DeepSeek Harness 插件 — 通过读取企划书 / 半成品软件 / 资料预估特定模型的 token 消耗量并实时按各家定价计费