Use when starting a session on a project with memory files or AGENTS.md after a gap, after changing backend services or API configurations, after adding features or packages, or…
Use when performing state-changing operations, recovering sessions, creating handoffs, or managing context freshness
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems.
Generate a compressed project context map to reduce token waste from codebase exploration. Pre-scans structure, detects frameworks, routes, imports, env vars, and estimates token…
Pre-execution mapping of codebases, document collections, or problem spaces. Runs BEFORE any Gorgon workflow to give all agents shared situational awareness
Map relationships between bounded contexts using DDD context mapping patterns. Use when defining upstream/downstream relationships, integration strategies (ACL, OHS, PL), or…
Entry point to the Context Mate toolkit - skills, agents, and slash commands that work with Claude Code's natural flow.
IntBrain context и memory. Используйте для context packs, memory search/store и graph links через canonical IntBrain tools.
Fleet worker contract for wiring assigned files to the v3 right-click menu. Use when handed files from pnpm check:context-menu, or told to 'wire the menu on X', 'do your assigned…
The universal v3 right-click menu (EditableContextMenu / NonEditableContextMenu). Use when adding a right-click menu to a surface, fixing a fake menu with no Copy or Export, a…
Knowledge about the context branch methodology for separating AI configuration from project code using git worktrees.
Use continuously during long tasks. Teaches how to read less, output less, and keep the LLM context window lean and fast.
Query, list, inspect and purge entries stored by the Context Mode hook (PostToolUse intercept of verbose outputs). Requires --with-context-mode to have been run at install time.
Monitors context token usage and warns when approaching limits. Automatically activates when context usage exceeds thresholds (30k, 50k, 70k tokens).
Display comprehensive project status dashboard showing current feature, pipeline phase, task progress, memory health, and recommended next actions.
Bootstrap, maintain, and evolve context networks across their full lifecycle. Use when starting a new project, when existing documentation feels scattered, or when agent…
Provide new contributors and agents with a concise tour of the workspace identity files (SOUL.md, USER.md, AGENTS.md, TOOLS.md) plus onboarding tips.
Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when impl — from…
Long context optimization with self-editing — extract key information, compress, summarize, and auto-prune stale context using the H2O + Context-1 patterns.
Context Optimization - Orchestrate RPI workflow TODO generation with interactive scoping
Format and structure data files for optimal Claude reasoning and extraction. Use when: (1) Preparing documents/data for Claude analysis, (2) User asks to 'optimize context' or…
Automatically optimizes context window usage when filling up (>70%). Uses hierarchical summarization, selective file loading, and intelligent compaction to maintain conversation…
Algorithm for assembling a small, deterministic set of relevant wiki pages to load before any /query, /ingest, or synthesis operation.
Build a compact, high-signal context brief (files, symbols, recent commits) instead of pasting large code blocks
Parallel historical context gathering using G-4 CONTEXT. Deploy 6 probes to gather all relevant context before complex work.
Solve context fragmentation across Claude sessions. Use when users mention re-explaining themselves, losing conversation context, starting over, "you forgot," context loss,…
Waypoint plans methodology and session survival patterns for Claude Code. Use when working on long-running features, need to resume after context reset, want to document task…
Decide where in a prompt to put documents, history, and instructions, given that models attend unevenly across a long context.
Use when designing stateless execution contracts, applying context compression strategies, or auditing context budget governance
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
Context preservation patterns for storing work results and session context via an MCP-compatible context server.
Automatically save and restore development context to minimize cognitive load when resuming work. Use when switching tasks, taking breaks, or returning after interruptions.
Load full project context before starting work. Use at the beginning of any session, when switching projects, or when the agent seems to have lost context about the codebase.
Rules for passing ctx: Context as the first parameter to internal methods so that @trace.span() produces connected trace hierarchies.
How agent runtimes dynamically prune stale tool outputs, dead build logs, and historical turns to eliminate quadratic token growth ($O(N^2)$) and prevent attention degradation.
Use before starting a non-trivial coding task to gather the relevant repository context (README, docs, ADRs, related modules, recent git history) and distill it into a short…
Rank an existing set of context chunks by relevance, diversity, freshness, and utility. Use when retrieval has already produced candidates that must be scored or reranked; use…
Query past decisions, bets, learnings, and documents by topic
Emit privacy-safe receipts for context selection, deferral, hydration, compaction, pruning, delegation, usage attribution, and boundary handoffs.
Use at the start of every session, and especially after context compaction or a cold restart. Fires as the first action, before engaging with the user's opening message.
Inicjalizacja i odświeżenie kontekstu projektu. Intencje: załaduj/odśwież kontekst, wczytaj dokumenty startowe, sprawdź stan repo.
Prepare a branch-scoped handoff before context saturation while preserving the current atomic step and loading boundaries.
Restore previous session state from Serena MCP checkpoints. Retrieves checkpoint by ID or auto-selects most recent, deserializes context, restores command/skill/phase/wave state.
EN: Triggered when user says "restore context", "continue", or similar in English. ZH: 当用户说中文"恢复上下文"、"恢复"、"接着"、"继续之前的工作"时触发。 IT: Si attiva quando l'utente dice "ripristina…
Retrieve relevant episodic context from memory for informed decision-making. Use when you need past episodes, patterns, or solutions to similar tasks.
Deterministic 3-cycle loop for gathering codebase context before acting. Broad search → exact source and tests → target-specific docs and setup.
Context retrieval patterns for accessing session context via an MCP-compatible context server. Provides patterns for browse and retrieve, hybrid search, semantic search, and…
Review CLAUDE.md files for quality, efficiency, and structure. Use when auditing LLM context files, checking documentation organization, preparing for context optimization, or…
Personal knowledge base integration via Obsidian vault. Provides semantic search, note retrieval, and context loading for Claude Code sessions.
Intelligent intent detection and skill routing gateway. Analyzes user prompts for keywords, patterns, and project context to automatically activate the correct specialized skill.
Determines minimal context and routes tasks to the correct prompts, agents and tools.
Save decision, bet, or learning to the context registry
Use when: you need strict context boundaries in chat (Telegram/Discord/Slack/etc.) and want to prevent topic bleed using explicit tags like [ISO], [SCOPE], [GLOBAL], [NOMEM],…
Check whether the current session is approaching context limits. Routes to compact or handoff.
Generate comprehensive context-setting markdown files for coding tasks by intelligently exploring codebase and structuring work with ROLE, CONSTRAINTS, STYLE, file reading order,…
Build, import, or refresh this workspace's identity, project, reusable-workflow, and weekly-state files through a guided review.
Offload large / multi-file reads to a cheap worker model so raw files never enter Claude's context (token savings)
Audit all auto-loaded Claude Code context files (CLAUDE.md chain, .claude/rules/*.md, MEMORY.md) for a project and produce a prioritized progressive-disclosure improvement report…
Split large CLAUDE.md into child files. Use when context files exceed line limits, are too verbose, or cover multiple distinct topics that should be separate.
Load this workspace's current state, recent decisions, blockers, priorities, and session continuity, then give a concise briefing.