context-budgetlisted

# context-budget ## Overview Audit what's eating my Claude Code context — skills, MCP servers, the CLAUDE.md chain, and my growing memory — and produce a prioritized list of what to trim. The point is keeping the **whole setup** lean, not just the pack. This is skill #11, a conscious break of the original 10-cap (since raised again, 11→12, for `exploit-hunt`), justified by token economy being a recurring concern. ## When to use - Context feels heavy / output quality slips, or `/context` shows a big always-on chunk. - I've added skills, agents, or MCP servers, or `MEMORY.md` keeps growing. - Before adding more — to know if there's headroom. ## The key model: always-on vs on-demand - **Always loaded** (every turn): skill `description` lines, MCP tool schemas, the CLAUDE.md chain, and **`MEMORY.md`** (the memory index). This is the real budget — trim here first. - **On-demand** (only when invoked): a skill's SKILL.md body, an agent's prompt. Cheap — a long body costs nothing until it runs, so don't optimize bodies. ## How it works ### 1. Inventory - **Skills:** `make details` (or `claude plugin details <plugin>`) for the pack's projected token cost; note each `description` length (always-on). - **MCP servers:** count servers and tools (~500 tokens of schema per tool, always-on). Flag servers with many tools, or that just wrap a CLI I already have (`gh`, `git`, `supabase`). - **CLAUDE.md + memory:** size of the CLAUDE.md chain and `MEMORY.md` + `memory/*.md`. The