← ClaudeAtlas

mkcontext-auditlisted

Read-only audit of `.claude/` structural overhead. Reports prioritized "remove X save Y tokens" recommendations against the model context window. NOT for monetary cost tracking — that's /mk:budget. NOT for transcript size monitoring — long-session continuity defers to Claude Code native compaction. Use when planning to add context capacity, diagnosing perceived slowdowns, or auditing health.
ngocsangyem/MeowKit · ★ 14 · AI & Automation · score 85
Install: claude install-skill ngocsangyem/MeowKit
# /mk:context-audit — Context Window Structural Audit Read-only audit of `.claude/` structural overhead. Surfaces what is loaded into every host-runtime session and how much of the context window it consumes, then recommends the highest-leverage trims. ## When to Use Three concrete triggers: 1. **Pre-add capacity check** — before adding a new agent, skill, or rule file, confirm the project is below the 25% structural-overhead threshold. 2. **Post-degradation diagnostic** — when sessions feel slow, off-topic, or over-compacted, audit to see if structural overhead has grown past 10%. 3. **Periodic health audit** — quarterly or on model upgrades, confirm the always-on bundle still pays its keep (paired with the dead-weight audit in `harness-rules.md` Rule 7). ## Context vs Cost (Boundary) | Concern | Mechanism | Unit | | ------------------------------- | -------------------------------------------------------- | ------------- | | Monetary cost | `/mk:budget` + `harness/scripts/budget-tracker.sh` | USD | | Window utilization (this skill) | `/mk:context-audit` + `scripts/inventory-context.sh` | tokens / % | The three concerns are deliberately separate. This skill measures only what is **statically loaded** into every session — the always-on bundle. Conversation history, tool output, and active edits live elsewhere. ## Workflow The slash co