context-budget

Skill: Context Budget

When to use

At the start of any task, and whenever you're about to read files to gather context. Keeps you from burning tokens by scanning the whole repo when a targeted read would do.

The principle

Context is a budget. Spend it on the few files that matter for the task, not on re-reading everything every session. SmartStack exists so you can load summaries instead of raw code.

Procedure

1. Start from the index, not the filesystem. Read ai-rules/context/file-map.md to locate things instead of recursive directory listing. Read ai-rules/context/project.md for what the project is and its current state. These answer most "where/what" questions.
2. Load only the rule(s) for the domain you're touching. UI task → rules/frontend.md. DB task → rules/database.md. Don't load all rules for a one-line change.
3. Use memory by index. For "did we hit this before?", read memory/errors/INDEX.md and jump to the matching entry — don't read every past error. Same for memory/sessions/INDEX.md.
4. Open source files just-in-time. Read a file right before editing it, and read the specific function/section when the file is large (use a line range), not the whole thing.
5. Prefer the data/API summaries. context/data-model.md and context/api-map.md usually answer schema/endpoint questions without opening the code.
6. Don't paste large blobs into prompts. Reference the path; let the reader open it if needed.

Rules of thumb

• One focused task = a handful of files, not the repo.
• If you've read a summary, don't also read the full thing "to be safe."
• Keep your working notes short; let the memory files hold detail.
• If the task is big, split it — smaller scope reads fewer files and produces better output.

Output

When you start a task, briefly state which context files you loaded and why. Makes the budget visible.