context-engineering
/context-engineering
Optimize Claude Code context-window usage for accuracy and cost. TRIGGER when: hitting context limits, structuring prompts for an agent, or trimming what gets injected into a task. SKIP: persisting knowledge across sessions (use agent-memory); semantic recall tuning (use semantic-memory-mcp).
- Author
- komluk ↗
- Repository
- scaffolding ↗
- Licence
- MIT
- Last repository change
- 27.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Optimize Claude Code context-window usage for accuracy and cost. TRIGGER when: hitting context limits, structuring prompts for an agent, or trimming what gets injected into a task. SKIP: persisting knowledge across sessions (use agent-memory); semantic recall tuning (use semantic-memory-mcp).
Original author description
Optimize Claude Code context-window usage for accuracy and cost. TRIGGER when: hitting context limits, structuring prompts for an agent, or trimming what gets injected into a task. SKIP: persisting knowledge across sessions (use agent-memory); semantic recall tuning (use semantic-memory-mcp).
How it works
- Auto-Invoke Triggers
- Context Principles
- Context Analysis Process
- CLAUDE.md Structure
- Always-loaded vs lazy path-scoped rules
- Optimization Strategies
- Context Health Metrics
- Maintenance Schedule
- Output: Context Report
SKILL.md preview
--- name: context-engineering description: "Optimize Claude Code context-window usage for accuracy and cost. TRIGGER when: hitting context limits, structuring prompts for an agent, or trimming what gets injected into a task. SKIP: persisting knowledge across sessions (use agent-memory); semantic recall tuning (use semantic-memory-mcp)." --- # Context Engineering Skill Optimizes Claude Code context for better performance and accuracy. Tracked files in repo: !`git ls-files 2>/dev/null | wc -l || true` ## Auto-Invoke Triggers - Every 50 messages in conversation - After major refactoring - When context feels stale - Task switching - User requests `/context` command ## Context Principles ### Active Curation - Keep only relevant information - Remove completed task details - Archive outdated patterns - Focus on current work ### Signal-to-Noise Ratio | High Signal | Low Signal | |-------------|------------| | Current APIs | Old experiments | | Active patterns | Completed tasks | | Recent decisions | Historical context | | Project structure | Implementation details | ### Token Budget | File | Limit | Purpose | |------|-------|---------| | CLAUDE.md | < 2000 tokens | Quick reference | | Agent docs | < 500 per agent | Role definition | | Skills | < 300 per skill | Methodology | ## Context Analysis Process ### Step 1: Measure Current State ```markdown ## Context Analysis ### Token Counts - CLAUDE.md: XXX tokens - Agent docs: XXX tokens total - Skills: XXX tokens total - Total: XXXX tokens ### Staleness Check - [ ] Last updated: [date] - [ ] References current project state - [ ] No deprecated APIs/patterns ``` ### Step 2: Identify Issues ```markdown ### Issues Found #### Stale Content - Section X: Outdated [reason] - Section Y: No longer relevant #### Redundant Content - Duplicated in files A and B - Can consolidate X and Y #### Missing Content - Current API not documented - New pattern not captured ``` ### Step 3: Optimization Actions ```markdown ### Optimization Plan 1. **Archive**: Move section X to knowledge-core.md 2. **Remove**: Delete duplicate Y 3. **Update**: Refresh API documentation 4. **Add**: Document new pattern Z ``` ## CLAUDE.md Structure Optimal structure for quick reference: ```markdown # Project Name [One-line description] ## Quick Reference | Action | Command | |--------|---------| | Run | command | | Test | command | | Build | command | ## Agent System [Link to detailed docs] ## Tech Stack - Frontend: [stack] - Backend: [stack] ## Project Structure [Key directories only] ## Key Rules 1. [Critical rule] 2. [Critical rule] ``` ## Always-loaded vs lazy path-scoped rules CLAUDE.md content splits into two tiers by *when* it must be available: | Tier | Lives in | Loads | Examples | |------|----------|-------|----------| | **Always-loaded** | project-root `CLAUDE.md` | every message, before any file is touched | routing Protocol + Decision Tree + Agents table | | **Lazy / path-scoped** | nested `CLAUDE.md` in a subdir | only while editing under that directory tree | per-area code conventions, stack notes, types location | **Hard rule:** the routing sections NEVER move into a nested `CLAUDE.md` — routing must fire on the first message, but a nested file only loads on Edit/Write under its tree (too late to route). Only path-specific *code conventions* are candidates to relocate, and only via the opt-in `/init-rules` scaffolder. This trims always-loaded tokens (modest for the plugin CLAUDE.md, larger for heavy project repos) without weakening routing. `/doctor` asserts the routing section is still present in the root CLAUDE.md. ## Optimization Strategies ### Token Reduction - Use tables instead of prose - Link to details instead of inline - Remove examples from main docs - Keep explanations brief ### Information Hierarchy 1. **Immediate**: In CLAUDE.md 2. **Reference**: In linked docs 3. **Archive**: In knowledge-core.md 4. **Delete**: Truly obsolete ### Import Chain Management - Max 5 levels of imports - No circular references - Clear dependency direction ## Context Health Metrics | Metric | Healthy | Warning | Critical | |--------|---------|---------|----------| | CLAUDE.md tokens | < 1500 | 1500-2500 | > 2500 | | Stale sections | 0 | 1-2 | 3+ | | Redundancy | 0% | < 10% | > 10% | | Missing critical | 0 | 1 | 2+ | ## Maintenance Schedule | Trigger | Action | |---------|--------| | Every 50 messages | Quick analysis | | After major change | Update relevant sections | | Weekly | Full review | | Task switch | Clear task-specific context | ## Output: Context Report ```markdown ## Context Report **Date**: [date] **Health**: Healthy | Warning | Critical ### Metrics - Total tokens: XXXX - Stale sections: X - Redundancy: X% ### Findings 1. [Finding] 2. [Finding] ### Recommendations 1. [Action to take] 2. [Action to take] ### Potential Savings - Current: XXXX tokens - After optimization: XXXX tokens - Savings: XX% ```
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · komluk/scaffolding | 100 | MIT |
| mvschwarz/openrig | 100 | Apache-2.0 |
| TerminalSkills/skills | 100 | Apache-2.0 |
| FrancoStino/opencode-skills-collection | 100 | MIT |
| drvoss/everything-copilot-cli | 100 | MIT |
| kdlbs/kandev | 100 | AGPL-3.0 |
| proxify-dev/agentic-kit | 100 | MIT |
| krzysztofsurdy/code-virtuoso | 100 | MIT |
| sickn33/agentic-awesome-skills | 100 | MIT |
Database snapshot: 13.11.2026 · package version c97fe7e17458 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90vc:context-engineering
Check context limits, optimize token usage, and debug context failures. Use when asking about rate limits, usage warnings, memory systems, or context-aware agent design. - 90vc:context-engineering
Check context limits, optimize token usage, and debug context failures. Use when asking about rate limits, usage warnings, memory systems, or context-aware agent design. - 100agent-memory
Use when an agent needs state that survives a session or a context compaction. Covers what to persist, file-based memory, structuring notes for retrieval, and preventing memory from becoming stale. Trigger on "agent forgets everything between sessions", "agent keeps retrying the… - 100check-context
Accurately check current context window and token usage. Use when the user asks about context usage, token consumption, or when monitoring context levels. - 90dev10x:context-audit
Audit context window utilization — CLAUDE.md files, rules, agent specs, references, and memories. Reports budget compliance, flags oversized files, and suggests pruning actions. TRIGGER when: user wants to optimize context usage, after adding many rules or memories, or when… - 100evaluate-context-engineering
Context-engineering audit (C1-C6) of skills and always-loaded rules. Use when trimming context bloat, auditing a plugin, or after a new Claude model ships.