/smart-loader
Automatically suggests optimal files to preload based on the user's task description and historical context patterns. Activates when the user starts a new task, mentions reading files, or when session context is being set up.
$ npx -y skills add egorfedorov/claude-context-optimizer --skill smart-loader --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/smart-loader
Context preview
The summary Claude sees to decide when to auto-load this skill.
Automatically suggests optimal files to preload based on the user's task description and historical context patterns. Activates when the user starts a new task, mentions reading files, or when session context is being set up.
SKILL.md
smart-loader.SKILL.mdname: smart-loader
description: Automatically suggests optimal files to preload based on the user's task description and historical context patterns. Activates when the user starts a new task, mentions reading files, or when session context is being set up.
license: MIT
disable-model-invocation: false
Smart Context Loader
When a user starts a new task or asks to work on something, check if there are historical patterns that suggest which files they'll need.
When to Activate
- User describes a new task (bug fix, feature, refactor, review)
- User says "let's work on..." or "I need to fix..."
- Session just started and user is describing what they want to do
- User asks "what files do I need for this?"
How to Use
1. Check for existing templates matching the task type:
ls ~/.claude-context-optimizer/templates/ 2>/dev/null
2. Check historical patterns for the current directory:
node ${CLAUDE_PLUGIN_ROOT}/src/tracker.js suggest "$(pwd)"3. Based on the task description and historical data:
- If a matching template exists, mention it: "I see you have a '{name}' template. Want me to load that context?"
- If historical patterns suggest files, mention: "Based on previous sessions, you usually need these files for this type of task: ..."
- If patterns show files to avoid, mention: "Tip: [file] has been consistently unused in past sessions — I'll skip it."
- If nothing matches, proceed normally
Auto-Optimization Tips
When you detect patterns that waste tokens, proactively suggest improvements:
- If a large file (300+ lines) is being read fully: "I'll use offset/limit to read only the relevant section"
- If a file was wasted in 2+ past sessions: skip it silently or mention why
- If the user's task matches a known template: offer to apply it
Important
- Do NOT automatically read files without user confirmation
- Only SUGGEST, don't force context loading
- Keep suggestions brief (top 3-5 files max)
- If no tracking data exists yet, skip silently — don't mention the optimizer
- Be helpful, not annoying — max 1 suggestion per task start
Read more
name: smart-loader description: Automatically suggests optimal files to preload based on the user's task description and historical context patterns. Activates when the user starts a new task, mentions reading files, or when session context is being set up. license: MIT disable-model-invocation: false
Smart Context Loader
When a user starts a new task or asks to work on something, check if there are historical patterns that suggest which files they'll need.
When to Activate
- User describes a new task (bug fix, feature, refactor, review)
- User says "let's work on..." or "I need to fix..."
- Session just started and user is describing what they want to do
- User asks "what files do I need for this?"
How to Use
1. Check for existing templates matching the task type:
ls ~/.claude-context-optimizer/templates/ 2>/dev/null
2. Check historical patterns for the current directory:
node ${CLAUDE_PLUGIN_ROOT}/src/tracker.js suggest "$(pwd)"3. Based on the task description and historical data:
- If a matching template exists, mention it: "I see you have a '{name}' template. Want me to load that context?"
- If historical patterns suggest files, mention: "Based on previous sessions, you usually need these files for this type of task: ..."
- If patterns show files to avoid, mention: "Tip: [file] has been consistently unused in past sessions — I'll skip it."
- If nothing matches, proceed normally
Auto-Optimization Tips
When you detect patterns that waste tokens, proactively suggest improvements:
- If a large file (300+ lines) is being read fully: "I'll use offset/limit to read only the relevant section"
- If a file was wasted in 2+ past sessions: skip it silently or mention why
- If the user's task matches a known template: offer to apply it
Important
- Do NOT automatically read files without user confirmation
- Only SUGGEST, don't force context loading
- Keep suggestions brief (top 3-5 files max)
- If no tracking data exists yet, skip silently — don't mention the optimizer
- Be helpful, not annoying — max 1 suggestion per task start
Claude Code plugin that tracks token usage, identifies wasted context, and saves 30-50% on API costs. Heatmaps, ROI reports, budget alerts, efficiency scores, git-aware suggestions — all local, zero config.
Repo: egorfedorov/claude-context-optimizer
Other skills on claude-context-optimizer.
- /cco-anatomy
Generate a compact project map so Claude understands the codebase without opening every file
Open skill - /cco-budget
Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Opus 4.8 default, full 1M context at standard price)
Open skill - /cco-claudemd
Analyze CLAUDE.md files for token bloat and suggest optimizations
Open skill - /cco-clean
Clean up old tracking data and reset statistics
Open skill - /cco-coach
Analyze the user's last prompt for clarity, scope and specificity — give a quality score and concrete suggestions to make the next prompt produce better results
Open skill - /cco-digest
Show weekly/daily efficiency digest with score and trends
Open skill

