context-compression
Use when compressing agent context, implementing conversation summarization, reducing token usage in long sessions, or asking about "context compression", "conversation history", "token optimization", "context limits", "summarization strategies"
What this skill does
# Context Compression Strategies When agent sessions generate millions of tokens, compression becomes mandatory. Optimize for tokens-per-task (total tokens to complete a task), not tokens-per-request. ## Compression Approaches ### 1. Anchored Iterative Summarization (Recommended) - Maintain structured summaries with explicit sections - On compression, summarize only newly-truncated content - Merge with existing summary instead of regenerating - Structure forces preservation of critical info ### 2. Opaque Compression - Highest compression ratios (99%+) - Sacrifices interpretability - Cannot verify what was preserved ### 3. Regenerative Full Summary - Generate detailed summary on each compression - Readable but may lose details across cycles - Full regeneration rather than merging ## Structured Summary Format ```markdown ## Session Intent [What the user is trying to accomplish] ## Files Modified - auth.controller.ts: Fixed JWT token generation - config/redis.ts: Updated connection pooling ## Decisions Made - Using Redis connection pool instead of per-request - Retry logic with exponential backoff ## Current State - 14 tests passing, 2 failing - Remaining: mock setup for session service tests ## Next Steps 1. Fix remaining test failures 2. Run full test suite 3. Update documentation ``` ## Compression Triggers | Strategy | Trigger | Trade-off | |----------|---------|-----------| | Fixed threshold | 70-80% context | Simple but may compress early | | Sliding window | Last N turns + summary | Predictable size | | Importance-based | Low-relevance first | Complex but preserves signal | | Task-boundary | At task completions | Clean but unpredictable | ## The Artifact Trail Problem File tracking is the weakest dimension (2.2-2.5/5.0 in evaluations). Coding agents need: - Which files were created - Which files were modified and what changed - Which files were read but not changed - Function names, variable names, error messages **Solution**: Separate artifact index or explicit file-state tracking. ## Probe-Based Evaluation Test compression quality with probes: | Probe Type | Tests | Example | |------------|-------|---------| | Recall | Factual retention | "What was the original error?" | | Artifact | File tracking | "Which files have we modified?" | | Continuation | Task planning | "What should we do next?" | | Decision | Reasoning chain | "What did we decide about Redis?" | ## Compression Ratios | Method | Compression | Quality | Trade-off | |--------|-------------|---------|-----------| | Anchored Iterative | 98.6% | 3.70 | Best quality | | Regenerative | 98.7% | 3.44 | Moderate | | Opaque | 99.3% | 3.35 | Best compression | The 0.7% extra tokens buys 0.35 quality points—worth it when re-fetching costs matter. ## Three-Phase Workflow (Large Codebases) 1. **Research Phase**: Explore and compress into structured analysis 2. **Planning Phase**: Convert to implementation spec (~2,000 words for 5M tokens) 3. **Implementation Phase**: Execute against the spec ## Best Practices 1. Optimize for tokens-per-task, not tokens-per-request 2. Use structured summaries with explicit file sections 3. Trigger compression at 70-80% utilization 4. Implement incremental merging over regeneration 5. Test with probe-based evaluation 6. Track artifact trail separately if critical 7. Monitor re-fetching frequency as quality signal
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.