Sistema de compactación de contexto para evitar saturación de la ventana de contexto. Guarda decisiones, pasos, y contexto en archivos markdown organizados.
LSP-powered context extraction using cclsp MCP tools, Solargraph, and Sorbet for type-safe code generation.
When agent sessions generate millions of tokens of conversation history, compression becomes mandatory.
When agent sessions generate millions of tokens of conversation history, compression becomes mandatory.
Context compression and summarization methodology. Techniques for reducing token usage while preserving decision-critical information.
Claude Code-optimized context transfer for development workflows. Preserves code context, git state, running services, and development environment when moving work betwee — from…
Claude Code-optimized context transfer for development workflows. Preserves code context, git state, running services, and development environment when moving work betwee — from…
Report harness context overhead (KB, words, estimated tokens) for a given path by walking the directory tree and collecting all CLAUDE.md, agents.md, and @-import files the Claude…
Map Claude Code harness context overhead across the ENTIRE AIOS as an ASCII tree — brute-forces every directory under $HORIZON_ROOT, attributes each auto-loaded CLAUDE.md /…
The brownfield back-fill. Routed to by /create-context, and by startup when .codearbiter/CONTEXT.md lacks the body marker but source code exists.
Compress tool outputs, logs, and JSON before they enter the context window — structural compression via a deterministic stdlib script (schema + samples + stats instead of 300 raw…
Framework for managing project file context after retros/planning. Trigger after weekly retro + planning complete, after monthly retro + planning complete, or when context feels…
Context curation for multi-agent pipeline handoffs with summarization, filtering, chunking, state management, handoff validation, and budget tracking.
Language models exhibit predictable degradation patterns as context length increases. Understanding these patterns is essential for diagnosing failures and designing resilient…
Recognize patterns of context failure: lost-in-middle, poisoning, distraction, and clash
Route data-related requests to the right Monte Carlo skill or workflow. USE WHEN alerts, incidents, data broken, stale, coverage gaps, data quality, or any ambiguous data…
Optimize Claude Code context window usage. Identify what to keep in context vs fetch on-demand. Use when context is bloated, responses are slow, hitting token limits, or want to…
Build CONTEXT.md (domain glossary) + docs/adr/ via interview; keeps agent vocab aligned. Triggers "domain language", "glossary", "ADR", inconsistent terminology.
Maintain short, focused Markdown files per subsystem to provide agents with isolated context.
Reduces token waste in Claude Code sessions. Scans projects to automatically generate .claudeignore files, and guides on over-read files and /clear timing.
Use when the user says "create context", "document this area", or wants a structured snapshot of a codebase area for agent orientation.
上下文驱动开发 - （专业版）。可剖析提升工作效率. 当需要context driven dev tool相关能力的开发场景,提供工作流程和配置参考。为新项目创建完整的上下文文档体系。**示例指令**：` `初始化新项目的上下文。适用于独立开发者、企业团队和自动化工作流场景，提供结构化输出与错误处理机制，支持中文交互，即开即用
Guide for implementing and maintaining context as a managed artifact alongside code, enabling consistent AI interactions and team alignment through structured project…
Create or update a task context dump document by scanning existing content and appending only new, non-duplicative progress.
DX V3 workflow system, skills, slash commands, Beads issue tracking, and Serena code navigation. Handles skill creation, command configuration, workflow automation, and…
Monitors context window capacity, routes tasks to minimal member set, and triggers session triage. Use when managing session capacity.
Close a workspace session by reviewing a proposed summary, recording approved outcomes, updating state and decisions, and checking repository safety.
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context during conversations, and…
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules file — from…
Distill learnings from a completed repo analysis into reusable knowledge base entries in ~/.copilot/context/.
Specifies rules for managing context files, including the master project context and supplementary files, emphasizing stability and change management.
Auto-spawn context-finder agent for search tasks. Use when user says "find", "search", "where is", "look for", "trace", "what file", "which commit", "grep", "locate".
Use when executing complex sub-tasks that need context isolation - creates branches with token budgets that auto-cleanup on return
Context is the complete state available to a language model at inference time. It includes everything the model can attend to when generating responses: system instructions, tool…
Understand what context is, why it matters, and the anatomy of context in agent systems
Gather comprehensive context from Forgetful Memory, Context7 docs, DeepWiki, and web sources before planning or implementation.
Procedura per governare la compattazione del contesto. Usala quando arriva un segnale CONTEXT BUDGET (hook context-budget.sh) o quando l'utente cambia task, per proporre /compact…
Use when storing decision traces, querying past precedents, or implementing learning loops. Load in COMPLETE state or when needing to learn from history.
PERMANENT — actif dès le début de chaque session et sur tous les tool calls. Économie de tokens (contexte = 200k, tool outputs = 84% de l'usage) et style de sortie.
Guardiao de contexto que preserva dados criticos antes da compactacao automatica. Snapshots, verificacao de integridade e zero perda de informacao.
Creates context handoff documents for session continuity. Use when ending sessions, switching tasks, or handing off work.
Use when validating or diagnosing the cortex environment (consistency, duplicates, redundancy, optimization) - provides a diagnostic workflow and reporting structure for context…
Design memory hierarchy with progressive loading for optimal context management. Use when organizing CLAUDE.md imports, implementing just-in-time context loading, or designing…
Use Context Hub (chub) for curated, versioned API/SDK docs and agent skills. Keep OpenAI tasks on official docs first.
Use when setting up new development environment or troubleshooting MCP connectivity. Configures Context Hub dependencies including Forgetful MCP server and plugin prerequisites.
Context isolation and subagent barrier patterns for clean workflow loops. 隔絕上下文，杜絕污染，保循環清潔. Use when: prevent context leak, isolate subagent, manage loop state, enforce context…
Keep long-running agent conversations healthy with attachment filtering, tool-result budgeting, snip and microcompact passes, context collapse, autocompact, reactive recovery, and…
Configure the context window statusline indicator
Always Auto-invoked skill that creates/updates workspace AGENTS.md to instruct the agent to always search for existing skills before attempting any scientific task.
Place trusted contextual information into prompts or agent state using explicit boundaries, provenance, and templates.
Use when the PLAN artifact from SAM Stage 2 needs contextualization against actual codebase state — grounds the design plan in reality by performing scope analysis…
Interview an analyst to build or improve an ACF analytics-context repo, including metrics, entities, caveats, eval seeds, and a five-question test drive.
Guides you through creating context items — instructions, skills, knowledge pointers, and memory events — that give the AI analyst persistent knowledge about your organization.
Trigger: user is using context.WithValue or asking about context keys, storing values in context, or finding that context values are missing or wrong at runtime.
Evaluate, adapt, and safely install Context Kit personal context artifacts for Claude Code or adjacent agent workflows.
Synthesizes recent organizational activity into a durable context wiki. Use when running a nightly or incremental context-layer dream, or when updating sourced organizational…
CLAUDE.md と依頼文から案件の前提・制約・品質基準を抽出し、context artifact としてサマライズする。Use when: 新しい TASK に着手する前、WF-01 Context Bootstrap 開始時、前提情報を整理したい時。
Session start context priming -- loads relevant memories from Pensyve at the beginning of a session to provide continuity across sessions.
Decide which agents and skills to load for a given task. Use at the start of every task to select the minimum viable context load, calculate the token budget, and stay below the…
Create and update .opencode/context-log.md to preserve issue context and checkpoint history across compaction and session handoffs