token-usage-auditor
Token Usage Auditor
Measure token usage as project telemetry: where agent attention went, how much fresh work versus cached context was spent, and which sessions or sidecar runs should be tied back to project phases and artifacts.
Skill Directory Layout
<installed-skill-dir>/
├── SKILL.md
├── scripts/
│ └── collect_token_usage.py
└── references/
└── data-model.md
Core Principles
- Treat token usage as attention and cost telemetry, not as quality by itself.
- Prefer local exact logs for Codex and Claude Code before asking the user for estimates.
More from a-green-hand-jack/ml-research-skills
project-init
Initialize an ML research project control root. Use for paper/code/slides repos, shared memory, GitHub Project alignment, agent guidance, worktree policy, and lifecycle handoffs.
39init-python-project
Initialize or enhance a Python/ML project. Use for new repos or forks needing production structure, uv environment setup, and research evidence docs.
37new-workspace
Create Git branches or worktrees for research code and paper versions. Use for experiments, baselines, rebuttal fixes, arXiv/camera-ready branches, and worktree memory.
36project-sync
Sync verified code-side experiment results into paper memory. Use when logs, reports, run docs, or user-confirmed metrics should become paper-facing evidence.
36init-latex-project
Initialize a LaTeX academic paper project. Use for new conference or journal papers needing templates, macros, venue preambles, and writing guidance.
36add-git-tag
Create annotated Git milestone tags. Use when completing a phase, releasing a version, or marking a research checkpoint.
36