Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.
git clone https://github.com/rohitg00/pro-workflow.git--- name: context-optimizer description: Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget. user-invocable: true --- # Context Optimizer Manage your context window and token budget effectively. ## Quick Diagnosis 1. Run `/context` to check current usage 2. If > 70% → compact now before it degrades 3. If > 90% → you're in the "dumb zone", compact immediately ## Optimization Strategies ### Immediate | Action | Saves | When | |--------|-------|------| | `/compact` | 30-50% context | At task boundaries | | Disable unused MCPs | ~5% per MCP | When switching domains | | Use subagents for exploration | Keeps main context clean | Heavy search/read tasks | | Fresh session via `/resume` | 100% reset | When starting unrelated work | ### Configuration Set proactive auto-compaction: ```json { "env": { "CLAUDE_AUTOCOMPACT_PCT_OVERRIDE": "50" } } ``` ### MCP Audit Keep <10 MCPs enabled, <80 tools total. Each MCP adds overhead to every request. ```bash /mcp # List active servers # Disable what you're not using ``` ### Prompt Engineering for Token Efficiency - Scope your prompts: "In src/auth/, fix the login bug" - Provide constraints: "Don't modify the middleware" - Give acceptance criteria: "Should return 429 after 5 attempts" - Avoid vague prompts: "Fix the code" (forces Claude to read everything) ### Subagent Delegation Heavy operations that generate lots of output should go to subagents: - Test suite output → subagent - Large file exploration → subagent - Documentation generation → subagent - Log analysis → subagent The main session stays clean while subagents handle the volume. ## Context Budget Planning | Phase | Target Usage | Action If Over | |-------|-------------|----------------| | Planning | < 20% | Keep plans concise | | Implementation | < 60% | Compact between files | | Testing | < 80% | Delegate to subagent | | Review | < 90% | Start fresh session | ## Token Efficiency ### Output Reduction (40-60% savings) - No sycophantic openers ("Sure!", "Great question!") - No closing fluff ("Let me know if you need anything!") - No prompt restatement before answering - Code first, explanation only if non-obvious - Structured output (tables, bullets) over prose - ASCII only: -- not em dashes, straight quotes not smart quotes ### Behavioral Efficiency - One-pass coding: complete solution, test once, stop if green - Read before write: never modify unread files - No re-reads: don't re-read unchanged files - Tool-call budgets: 20 (quick fix) to 80 (large feature) - Never iterate more than twice on the same failure ### Task Profiles Switch response style based on context: - **Coding**: code first, minimal explanation, simplest solution - **Agent/Pipeline**: structured output only, no prose, parseable - **Analysis**: finding first, tables over paragraphs, sourced numbers ## CLAUDE.md Optimization - Root CLAUDE.md: < 60 lines ideal, < 150 max - Move package-specific info to package-level CLAUDE.md - Move personal preferences to CLAUDE.local.md - Remove obvious or rapidly-changing information ## When Context Is Degraded Signs: - Claude repeats itself or forgets earlier context - Responses become generic or lose project-specific knowledge - Tool calls start failing for reasons that worked earlier Fix: 1. Manual `/compact` 2. If still bad: new session with `/resume` 3. For recurring issues: reduce CLAUDE.md size, disable MCPs
[{"step":1,"action":"Identify the text to optimize (e.g., long chat history, dense documents, or verbose prompts).","tip":"Use this skill when you notice the AI struggling with context or when token limits are approaching. Focus on sections with repetitive phrases or unclear antecedents."},{"step":2,"action":"Copy the text and paste it into the prompt template, replacing [TEXT_TO_OPTIMIZE].","tip":"For best results, include the full context you want preserved. The AI will prioritize keeping critical details while removing fluff."},{"step":3,"action":"Review the optimized output and manually adjust if needed (e.g., restore nuance or specific terminology).","tip":"Check for unintended meaning loss, especially with technical terms, names, or conditional logic. The AI may simplify complex ideas too aggressively."},{"step":4,"action":"Use the optimized text in your next interaction or save it for future reference.","tip":"Store optimized versions in a knowledge base or prompt library to avoid re-optimizing the same content repeatedly."},{"step":5,"action":"For sessions with persistent context issues, apply this skill iteratively to the entire chat history before continuing.","tip":"Combine with 'summarization' skills to further condense context while retaining key points."}]
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/rohitg00/pro-workflow/tree/main/skills/context-optimizerCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Optimize the following [CONVERSATION_OR_DOCUMENT] for clarity and token efficiency while preserving all critical context. Remove redundant phrases, shorten sentences, and consolidate ideas where possible. [CONVERSATION_OR_DOCUMENT]: [TEXT_TO_OPTIMIZE]
Original text (120 tokens): 'I was just reviewing the quarterly financial report that was released yesterday, and I noticed that there are some discrepancies in the revenue figures for the EMEA region. Specifically, the numbers for Q2 2023 seem to be lower than what was projected in the budget, and this is causing some concern among the leadership team. I wanted to bring this to your attention so we can discuss potential next steps.'
Optimized text (55 tokens): 'Reviewed the quarterly financial report (released yesterday). Noticed discrepancies in EMEA revenue for Q2 2023—actuals are below budget projections. This has raised leadership concerns. Need to discuss next steps.'
Key improvements:
- Removed filler phrases ('I was just', 'I noticed that', 'I wanted to bring this to your attention')
- Consolidated three sentences into one
- Removed redundant qualifiers ('some concern' → 'raised concerns')
- Preserved all critical context (report timing, region, issue, stakeholder concern, action needed)
- Reduced token count by 54% while maintaining meaning.skills-collection
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan