“context-budget”的搜索结果

检查Claude Code加载的智能体、技能、规则和MCP配置所占的信息量，估算词元数，找出过长或重复的定义，并按预计可削减的量为改进建议排序。

• 排查上下文迅速占满的原因
• 添加技能或MCP后检查配置
• 查找过长文件和重复指令

[omh] Context window or token budget at risk: plan compact context, token/cost budgets, summarization checkpoints, and overflow recovery before long agent work. Use when the user says: context-budget-review, context budget review, context budget, token budget review, token budget, prompt budget, prompt caching, prompt cache.

中文简介正在准备中。当前显示原文说明。

Plan projects that use large language models, from checking whether the task suits a model to designing processing stages. Estimate costs, choose single or multiple agents, and organize prototypes, structured outputs, and iteration.

中文简介正在准备中。当前显示英语简介。

• Checking whether a task is suitable for an LLM
• Designing a pipeline for batch analysis
• Estimating processing costs before development

Plan a session's context window like the budget it is — what loads up front, what gets linked instead, what stays fetch-on-demand, and how to keep the stable prefix cache-friendly so repeated turns cost cents instead of dollars. Use when asked my agent keeps blowing its context, plan what to load into the session, why is every turn so expensive, or design the context for this workflow. Produces the load/link/fetch allocation, the cache-aware prefix layout, the per-turn cost shape, and the eviction rules for when the window fills anyway.

中文简介正在准备中。当前显示原文说明。

Audit token consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations. Use when the context window is filling up too fast or before adding new components.

中文简介正在准备中。当前显示原文说明。

Keep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.

中文简介正在准备中。当前显示原文说明。

Use when a coding session is burning context fast, output is drowning in noise, the model keeps forgetting earlier decisions, or the user asks to reduce tokens, stop the verbose narration, work in a huge repo, or make a long session survive. Covers what to read, what to summarize, what to write to disk, and when to start fresh.

中文简介正在准备中。当前显示原文说明。

审核Claude Code上下文窗口在代理、技能、MCP服务器和规则中的消耗情况。识别膨胀、冗余组件，并提供优先的令牌节省建议。

中文简介正在准备中。当前显示原文说明。

Analyzes Claude Project context budget under the automatic-RAG-by-window model: knowledge files vs. threshold-exempt overhead (Skills, MCPs, CI, Memory). Two modes: Quick Diagnostic and Full Budget Audit. Use when user says "check my context budget," "how much context am I using," "is my project too big," "optimize my token usage," "tier my files," "optimize for RAG," "improve retrieval quality," "should I keep compressing," "am I over-compressing," "should I accept RAG mode." Also trigger on context pressure symptoms: "Claude forgets my instructions," "responses getting generic," "content not found in my knowledge files." Also use when a project audit scores Knowledge Architecture ≤ 3. Do NOT use for content placement decisions (use rootnode-memory-optimization if available), full project audits (use rootnode-project-audit if available), or behavioral tuning (use rootnode-behavioral-tuning if available). Run on Opus 5 or Sonnet 5 at `high` effort (both defaults); depth reduces on legacy models.

中文简介正在准备中。当前显示原文说明。

Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.

中文简介正在准备中。当前显示原文说明。

Runtime router for context decisions during a task — decide read-more / stop / ask / assume / delegate, pick a minimal read-set, and time compaction. Front-page mental model is Write / Select / Compress / Isolate; a lazy pattern index routes to 25 context-engineering patterns, one reference per decision. Use when context is near budget, a long session is degrading, you must choose what to read for a task, or you are deciding /compact vs /clear vs a sub-agent. NOT for structural .claude/ overhead audits (see mk:context-audit); NOT for owning persistence (see mk:memory); NOT for USD cost (see mk:budget).

中文简介正在准备中。当前显示原文说明。

How to MEASURE this repo instead of eyeballing it — interpret the loop-station context-budget trend (history.jsonl, thresholds, the tokenizer-switch gotcha), read a session trace, use the eval ledger (cost-per-success), and pick the right evidence tool (app-shots, smoke-deployed, db-counts, --check modes). Use when asked "is the harness bloating", "how big is CLAUDE.md really", "did this agent run actually succeed", "prove this works", "what evidence do we have", or when tempted to declare a capability (browser, tool) unavailable. For RUNNING the loop-station scripts, defer to the loop-station skill — this skill is interpretation + the wider evidence toolkit.

中文简介正在准备中。当前显示原文说明。

Agent context budget guard and artifact compression workflow. USE FOR: image-heavy QA, compare board review, screenshot batches, large keep/todo/task manifests, long notes handoff, and md/json diff summarization. Trigger this before reading or forwarding heavy artifacts when token growth is a risk.

中文简介正在准备中。当前显示原文说明。

Strict routing mode for prompts prefixed with `(best)`. USE FOR: any turn where the user explicitly wants the safest, smallest-context, highest-discipline execution path. This skill must route into context-budget-guard first, then continue into the task-specific workflow.

中文简介正在准备中。当前显示原文说明。

Claude Codeセッション全体のエージェント、スキル、MCPサーバー、ルールにわたるコンテキストウィンドウ消費を監査。肥大化や冗長コンポーネントを特定し、優先順位付けされたトークン節約推奨事項を生成。

中文简介正在准备中。当前显示原文说明。