toktrack
CLAUDE.md196 starsChanged 13 days agoMITView on GitHub
Ultra-fast AI CLI token usage tracker. Rust + simd-json + ratatui. 각 단계 완료 후 즉시 다음 호출. 확인 묻지 말 것. clarify는 plan mode에 진입하지 않는다 — PLAN을 대화에 인라인 제시 후 곧바로 /implement. 코드가 아닌 작업은 /implement 없이 진행 가능. types: feat|fix|refactor|docs|test|chore|perf scopes: parser|tui|services|cache|cli
The file
Files
toktrack
Ultra-fast AI CLI token usage tracker. Rust + simd-json + ratatui.
Quick Start
cargo build --release
./target/release/toktrackContext
| File | Content |
.claude/ai-context/architecture.md | Layers, paths, traits, data flow |
.claude/ai-context/conventions.md | Naming, TDD, error handling, commits |
Workflow
코드 구현 작업
/clarify → /implement → /verify → /review → /wrap각 단계 완료 후 즉시 다음 호출. 확인 묻지 말 것.
clarify는 plan mode에 진입하지 않는다 — PLAN을 대화에 인라인 제시 후 곧바로 /implement.
문서/마케팅/설정 작업
Plan Mode (선택) → 직접 작업코드가 아닌 작업은 /implement 없이 진행 가능.
Commands
make check # fmt + clippy + test (pre-commit)
cargo test # Run tests
cargo bench # BenchmarksCI/CD
PR → CI (3 OS) → main → release-please → Release PR → 5 platform builds + npmCommit Rules
{type}({scope}): {description}types: feat|fix|refactor|docs|test|chore|perf
scopes: parser|tui|services|cache|cli
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

