By saidwivedi
View token usage breakdown for each Claude Code session, with optional filtering by custom date ranges using `/token-usage N`.
Claude Code skills for AI/ML researchers.
| Research Collaborator | Results to Slides |
| research-collaborator | Guardrails your research workflow. Encodes principles from experienced researchers and applies them before you spend the GPU hours. Checks your hypothesis, catches known bugs and flags sloppy methodology. |
| results-to-slides | Discovers experiments from git history and output folders, collects images and metrics, generates editable PowerPoint presentations (.pptx). |
Also includes a utility skill:
| token-usage | Per-session token usage breakdown. /token-usage or /token-usage 30 for last N days. |
Add the marketplace in Claude Code:
/plugin marketplace add saidwivedi/research-skills
Install all plugins:
/plugin install research-collaborator@saidwivedi-research
/plugin install results-to-slides@saidwivedi-research
/plugin install token-usage@saidwivedi-research
Or install just the ones you need.
Skills are invoked via slash commands in Claude Code:
/research-collaborator - start a research collaboration session/results-to-slides 0301 0308 - generate a presentation for experiments from March 1-8/token-usage 30 - show token usage over the last 30 daysresults-to-slides:
python-pptx, Pillow, lxmlcv2 or ffmpeg for video poster frame extractionresearch-collaborator:
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub saidwivedi/research-skills --plugin token-usageDiscovers experiments from git/output folders, collects images and metrics, generates PowerPoint presentations.
Guardrails your research workflow — checks hypotheses, catches known bugs, flags sloppy methodology.
Analyze Claude Code session token usage, costs, trends, and anomalies
Discovers experiments from git/output folders, collects images and metrics, generates PowerPoint presentations.
Tracks Claude Code session usage (tokens, costs, skills, MCP, subagents) and sends data to a self-hosted dashboard.
Generate an explorable HTML report of Claude Code session usage — tokens, cache efficiency, subagents, skills, and the most expensive prompts — from local ~/.claude/projects transcripts.
Session intelligence for Claude Code — find why your sessions fail and fix them
Audit, fix, and monitor Claude Code context window usage. Find the ghost tokens.