Install in seconds

Install this skill

Copy the command and run it in your terminal. You can review the source before installing.

terminal

git clone https://github.com/mocasus/paleo

Works with Git. The repository opens in your current directory.

🗜️

AI EngineeringPython

Paleo JSON

Compacts JSON and other structured data by removing whitespace, collapsing arrays, and shortening keys to reduce token usage in LLM outputs, without breaking parseability.

11 stars0 forksAdded 2026/07/16

View source on GitHub Download ZIP

agent-skillsai-agentsai-efficiencyautomationclaudeclaude-codecodexcontext-windowcost-optimizationdeveloper-toolsgeminigemini-clihermeshermes-agentllmllm-agentsprompt-engineeringskillstoken-savingtokens

Documentation

README

From the original repository

paleo-json

Compact structured output. JSON / YAML / tables → minimal tokens, still valid.

Rules

Minify: remove whitespace between tokens (valid JSON stays parseable).
Collapse arrays of repeated shapes into a count + 1 example when the consumer allows.
Keep keys verbatim unless a documented short alias exists — never invent keys.
Preserve: values, types, order where it matters, escaping.
YAML: drop comments, shorten, keep indentation minimal but valid.
Numbers/booleans/null: never reformat in ways that change type.

Levels

lite: minify whitespace only (safest).
full (default): minify + collapse repetitive array tails.
ultra: minify + alias keys per a provided map.

Switch

paleo-json / compact json / minify on. pretty print off.

Gotchas

Always return valid, parseable output — a broken payload costs more than the tokens saved.
Don't alias keys unless the consumer expects them; default = keep keys.
Streaming/chunked JSON: minify only after the full object is known.

More from mocasus

Other Claude Code skills by this author in the directory.

Paleo Auto

Automatically detects long sessions, high token usage, or bulky context and enables the appropriate Paleo token-saving skills to optimize token consumption without manual intervention.

Paleo Budget

Enforces a hard token budget per task/response by tracking estimates, stopping before limits, and summarizing if exceeded. Helps when users specify a token cap or want to limit spending.

Paleo Converse

Condense prior conversation turns into a summary, merge near-duplicates, and keep recent messages verbatim to save context tokens without losing task state.

Paleo Summary

Condenses long tool outputs, logs, diffs, or documents into concise summaries while preserving key details. Use when you need to save context tokens on bulky payloads.

Paleo Trim Context

Automatically trim, summarize, or drop stale content from the context window to save tokens while preserving task state. Use during long sessions, large file dumps, or before calling expensive models.

Paleo Mode

Switches the agent to a terse output mode, reducing token usage by ~50-70% while keeping code, commands, and technical terms exact. Use when you need brief replies or want to save costs.

More AI Engineering skills

Paleo JSON is one of 222 AI Engineering skills cataloged on DirSkills.

Browse all AI Engineering skills →

Andruia Solutions Architect

Diagnoses new or existing AI project workspaces and defines an optimal technical roadmap in Spanish. Use at the start of a project for guidance on architecture and expert squad selection.

Andru.ia Skill-Smith

Designs, drafts, and deploys new AI skills following the Diamond Standard, generating documentation and registry integrations. Use when you need to create or extend agentic capabilities in a structured repository.

Andru.ia Niche Intelligence

Analyzes a project's specific niche to inject domain knowledge, regulations, and industry standards. Use after the niche has been defined to ensure the product aligns with sector-specific expectations.