20 tagged token-optimization, measured the same way as everything else here.
Browse within: context-engineering 88ai-coding-agents 86code-ge 86vibe-coding 86vibecoding 86agentic-skills 38ai-agent-skills 38efficiency 38ai-coding 36github-copilot 31github-copilot-training 31claude-code-plugin 18agent-runtime 16llm-tools 13
Skill Claude CodeCodex
Review how the lean-ctx ctx MCP tools performed in the current session and file upstream issues for confirmed problems. Use when the user asks to review/audit lean-ctx tool performance, says "lean-ctx review", asks why ctx tools failed or fell back to native tools, or wants to report a lean-ctx bug.
Skill Claude CodeCodex
You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.
Skill Claude Code
Use before reading whole files or grepping wide. token-goat commands (symbol, read, section, semantic, outline, map, refs, bash-output) return narrow slices at low token cost. /token-goat audit reviews a session for missed savings.
Skill Claude CodeCodex
A web crawler and scraper that searches with DuckDuckGo, fetches individual pages or whole sites, and returns clean Markdown intended for language models. It can also scrape pages that need JavaScript to display their content.
Skill Claude Code
Delegate complex tasks to OpenCode subagent, use when >=2 file modifications or batch operations.
Supersynergy/agent-token-saver-skill-router
Skill Claude Code
Use when an agent has many skills/tools/prompts and must cut prompt tokens by routing adaptively. Runs routing outside model context when possible, indexes metadata on disk, lazy-loads one primary plus up to four complementary support skills, and benchmarks savings across agents.
1508550385junnan-bot/Magic-Agent-Global-Rules
Skill Claude CodeCodex
Universal collaboration rules for AI coding agents. Covers output standards, token optimization (90% cache hit, 98% tool output reduction), requirements locking with anti-drift checks, context compression (9-section CC template at 85%), skill borrowing workflow, image fallback without vision models, code comment…
ishitmehta1-art/precise-response-skill
Skill Claude CodeCodex
Calibrates Claude's response length and format to minimise unnecessary token usage without sacrificing quality. Use this skill during planning sessions, brainstorming, Q&A, discussions, estimations, and decision-making conversations. Claude defaults to concise, direct answers and expands only when the complexity or…
Skill Claude CodeCodex
Prevents prompt-cache thrash and runaway token burn in long or image-heavy agent sessions. Load BEFORE reading images/screenshots (visual QA, render checks, UI verification, diagram review) in a conversation that already has substantial history, when running long agentic loops with periodic wake-ups, or when the user…
Skill Claude CodeCodex
A guide to reducing token use in Codex conversations, where tokens are the units of text sent to and from the language model.
Skill Claude CodeCodex
A two-way semantic compiler that compresses PRDs, codebases, research papers, and meeting notes into dense symbolic notation, and reconstructs them back into professional prose. Use this skill whenever the user writes SQUEEZE, EXPAND, DIFF, MERGE, SUMMARISE, LIST SQUEEZES, RECALL, SEARCH, DELETE, or EXPORT ALL — or…
Skill Claude CodeCodex
Skill "zipai-optimizer" from nickdesi/ZipAI, covering zipai: ultra-dense token optimizer, rules, 1. zero filler, 2. ambiguity and 3. prompt caching.
Skill Claude CodeCodex needs its repo
Render a large paste, clipboard, or file into a dense PNG image via pxpipe and load it into context as an image, so bulky content costs vision tokens (3x denser) instead of text tokens — with a verbatim appendix of any byte-exact tokens. Use when a message starts with "pipethis:", or the user says "paste as image"…