Articles tagged "budget management"

装修防增项避雷

2026-10-28 Big Model Skills 装修防增项报价单隐形消费 budget management

装修防增项避雷是一个面向装修业主的 Skill，专治装修过程中的增项、加钱、报价单解读、隐形消费、偷项漏项和预算超支问题。通过问答方式帮助业主识别报价单中的风险，降低预算失控的可能性。

personal-budget-planner：个人预算规划 Skill

2026-10-27 Big Model Skills 个人预算生活服务 budget management 支出分析 SkillHub

个人预算规划 Skill，由社区开发者发布，支持对话式预算分析与调整。

绩效考核结果应用器：绩效与薪酬联动分配工具

2026-10-26 Big Model Skills 绩效考核薪酬管理 HR工具绩效薪酬联动 budget management

绩效考核结果应用器是面向薪酬HR和HRBP的绩效-薪酬联动分配工具，支持强制分布和九宫格双模型切换，可自动完成调薪和奖金分配，内置预算超支预警与多种处理方案，并提供合规校验和回溯检查功能。

DSH Budget View：在 DSH 中查看额度与费用

2026-10-26 DeepSeek Harness plugin DeepSeek DSH Plugin budget management Credit limit monitoring

DSH Budget View 插件在输入栏和新会话页展示 Codex / OpenCode Go 额度、DeepSeek 余额、波峰/波谷状态，并按 DeepSeek 官方人民币峰谷价估算会话费用。支持配置刷新间隔、显示样式、费用货币与汇率模式。

dsh-plugin-quota: Real-Time Usage Meter + Next-Step Forecast + Budget Brake

2026-10-18 DeepSeek Harness plugin DeepSeek dsh plugin dsh-plugin-quota Token monitoring budget management

`dsh-plugin-quota` is a DeepSeek Harness plugin designed to address the issue that models cannot perceive resource consumption. It uses real-time dashboards and prediction algorithms to give models an intuitive view of token usage, budget progress, and estimated costs, enabling self-braking and pacing control. Core features include real-time tracking, system prompt injection, `/qm` panel queries, next-step estimation, and cross-plugin state sharing. The plugin requires zero configuration, supports custom pricing and budgets, and allows other plugins to access context state via a data contract mechanism.

dsh-cost: Evidence-First Token Cost Ledger for DeepSeek Harness

2026-08-31 DeepSeek Harness plugin DeepSeek dsh plugin dsh-cost Token cost budget management

dsh-cost is a plugin for DeepSeek Harness (DSH), designed to address the ambiguity of cost accounting caused by the mixing of information from different sources, by establishing an evidence-first token cost ledger based on persisted `assistant/message.usage` events. This plugin separates routing splits, evidence completeness, budget status, and current context pressure snapshots for clear presentation, and provides explicit fail-open/fail-closed budget checking mechanisms. Its core features include offline CLI cost calculation, a built-in stdio MCP server (exposing `cost_report` and `cost_check` interfaces), and a user-maintained price book support, with prices calculated per million tokens and differentiated between input and output.