context-loader
Load project context efficiently for Conductor workflows. Use when starting work on a track, implementing features, or needing project context without consuming excessive tokens.
When & Why to Use This Skill
The Context Loader skill optimizes how Claude interacts with complex codebases by efficiently managing project context for Conductor workflows. It solves the problem of 'context bloat' and high token consumption by using a prioritized loading protocol—targeting essential manifests, specs, and tech-stack documents while respecting ignore files and handling large assets intelligently.
Use Cases
- Initializing New Development Tracks: Automatically gather product vision, technical requirements, and project structure when starting a new feature to ensure the AI is fully aligned with the roadmap.
- Token-Efficient Codebase Exploration: Use git-based discovery to map out directory structures and file lists without reading every line of code, preserving the context window for actual logic.
- Streamlining Implementation Workflows: Prepare the environment for the /conductor:implement command by loading only the necessary spec.md and plan.md files relevant to the current task.
- Intelligent Large File Handling: Extract critical headers, imports, and exports from files over 1MB, allowing the agent to understand dependencies without exhausting token limits.
| name | context-loader |
|---|---|
| description | Load project context efficiently for Conductor workflows. Use when starting work on a track, implementing features, or needing project context without consuming excessive tokens. |
Context Loader Skill
Efficiently load and manage project context for Conductor's context-driven development workflow.
Trigger Conditions
Use this skill when:
- Starting work on a new track or feature
- User mentions: "load context", "project context", "get context"
- Beginning
/conductor:implementworkflow - Need to understand project structure without reading all files
Token Optimization Protocol
1. Respect Ignore Files
Before scanning files, check for:
.claudeignore- Claude-specific ignores.gitignore- Standard git ignores
# Check for ignore files
ls -la .claudeignore .gitignore 2>/dev/null
2. Efficient File Discovery
Use git for tracked files:
git ls-files --exclude-standard -co | head -100
For directory structure:
git ls-files --exclude-standard -co | xargs -n 1 dirname | sort -u
3. Priority Files (Read First)
| Priority | File Type | Examples |
|---|---|---|
| 1 | Manifests | package.json, Cargo.toml, pyproject.toml |
| 2 | Conductor | conductor/product.md, conductor/tech-stack.md |
| 3 | Track | conductor/tracks/<id>/spec.md, plan.md |
| 4 | Config | tsconfig.json, .env.example |
4. Large File Handling
For files over 1MB:
- Read first 20 lines (header/imports)
- Read last 20 lines (exports/summary)
- Skip middle content
Context Loading Workflow
1. Load CLAUDE.md (if exists)
2. Load conductor/product.md (project vision)
3. Load conductor/tech-stack.md (technical context)
4. Load current track spec.md (requirements)
5. Load current track plan.md (tasks)
Response Format
After loading context, summarize:
## Project Context Loaded
**Product**: [one-line summary]
**Tech Stack**: [key technologies]
**Current Track**: [track name/id]
**Active Phase**: [current phase]
**Pending Tasks**: [count]