tool-output-diet

Keeps 'later', 'not yet' and 'after X' answers to Claude's questions open: the question and your answer ride along with every message until the item is done or dropped.

Cleans dictated prompts before they are sent: filler words, spoken quotation marks, project names spelled as the project's docs spell them, and a Haiku pass for longer messages.

Keeps the Claude co-author trailer and the Generated-with footer out of your commits and pull requests.

Gives Claude a studio_state tool for a studio-layout video repository: one compact answer on where a video project stands. Silent in every other folder.

Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)

hooks

Token usage tracking, model cost attribution per agent, budget alerts, and optimization recommendations

24 skills · 1 command · 1 agent · hooks

Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.

1 skill

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

Action-first, ADHD-friendly output shaping for Claude Code.

1 skill · hooks

Query Trackio projects, runs, and metrics using the `trackio` CLI. Use when the user needs to list projects/runs/metrics, get summaries, or retrieve metric values from local Trackio databases. Supports both human-readable and JSON output formats. Covers project discovery, run inspection, metric querying, and system metrics. Designed for LLM agents and automation scripts.

1 skill