Linter + profiler + coverage — for agent context
Know what your agent actually loads.
ctxlint audits, profiles, and scores AGENTS.md, CLAUDE.md, .cursor/rules, and every other context file steering your AI coding agents — then shows what it costs you in tokens, on every single request.
❯ npx @tqakdev/ctxlint scan
Scanning agent context… 14 files · 4 tools
Context Health 0/100 · 3 errors · 11 warnings · 6 info
❯ npx @tqakdev/ctxlint fix --write
✔ merged 3 duplicates · removed 6 dead rules · pruned stale refs
Context per request18,630 tokens−60% ▼
Psst… this is what a real scan looks like
Stop confusing your AI.
Every duplicated, drifted, or contradictory rule silently taxes every request — in tokens you pay for and in output quality you don’t get. ctxlint answers the questions nobody could answer about your repo.
What loads?
Per tool, per directory, in load order — see exactly what each agent reads, and why.
What does it cost?
Token totals for the context injected into every request — per file, per tool, no guessing.
What’s broken?
Duplicates, contradictions, drifted copies, dead file references, and rules buried 200 lines deep.
Does it help?
Judge recent commits against your rules — catch violations, and dead rules that never fire.
one command in CI · zero config
Free forever.
Fueled by supporters.
ctxlint is MIT-licensed and always will be. If it saved you tokens — or sanity — a one-time donation funds the open-source team building new detectors, better profiling, and fewer confused agents.
one-time payment via Stripe · pick your amount at checkout · receipt included · no account needed