Каталог навыков агентов

On-chain token analysis — holder distribution, smart money tracking, risk scoring.

Audit a repository for token waste — find redundant context files, measure baseline, recommend optimizations

Audit historical Claude Code token usage from JSONL session files — shows total spend, cache hit rates, top costly sessi...

Evaluate and configure SPL token authorities (mint/freeze/close) with risk implications and best practices. Use for audi...

General token-efficiency habits for this kit's agents — prefer targeted search over full reads, precise @-mentions, peri...

Brokered short-lived provider credentials client in matrx-frontend (`lib/api/broker/`). Use when browser code needs a pr...

Brokered short-lived provider credentials client in matrx-extend (`src/lib/broker/`). Use when a feature needs a provide...

Token budget tracking and enforcement for Gastown convoy-level execution. Hard limits with pre-execution checking, per-c...

Agent basina token kullanimi takibi, maliyet optimizasyonu, butce limitleri ve ROI analizi. Session ve proje bazinda har...

Proactive token budget assessment and task chunking strategy. Use this skill when queries involve multiple large file up...

Offer a choice of response depth (25%/50%/75%/100%) with token estimates before answering, then answer at that level. Us...

Offers the user an informed choice about how much response depth to consume before answering. Use this skill when the us...

Analyze static code for token usage patterns, waste, and budget risks. Trigger: /token-budget

Analyze markdown files for token budget compliance

Token预算强制执行器 - 5标准完整实现： 1. 全局考虑：覆盖人/事/物/环境/外部集成/边界情况 2. 系统考虑：预算→消耗→预警→熔断→报告完整闭环 3. 迭代机制：PDCA循环，版本历史，反馈收集 4. Skill化：标准SKI...

Proactively monitors Claude conversation token usage and warns when approaching limits. Tracks usage patterns and predic...

Estimate and optimize AI/ML costs including token usage, context window management, batch processing, and caching strate...

Set up or run the token build pipeline — transform the DTCG tokens/*.json (source of truth) into platform artifacts (CSS...

Render a token-usage stat card from local Claude Code, Codex, Gemini CLI, and OpenCode session logs and commit it into t...

Use when the user asks about token usage, session cost, or wants to check optimization effectiveness.

- Run at the start of every session and whenever prompt sizes or tool calls begin to spike.

Triggers: token, conservation Minimize token usage through conservative prompting, work delegation, and quota tracking....

Measure before optimizing — estimate token counts locally with stated heuristics, price them at your model's rates, and...

Estimate and track token costs before work sessions - complexity, duration, resources

Track token usage and costs across agents for budget management

Cut LLM output tokens 40–70% by stripping grammatical scaffolding while preserving every fact — telegraphic output modes...

Plan wallet splits, allocations, vesting, and transparency for SPL token launches. Use when designing distribution chart...

Generates design token documentation with visual swatches and code examples. Use when documenting token values, creating...

Personal diagnosis of where your Claude Code + Cowork spend goes. Reads local transcripts, prints your conversation leng...

Token supply dynamics, vesting analysis, inflation modeling, and valuation frameworks for crypto tokens

Rubric for keeping Claude Code sessions cheap without losing quality — model tiering, cache hygiene, Read discipline, MC...

Milo's in-session operating discipline for maximizing useful work per token and preventing context/credit drain — the co...

Token budget manager. Sets per-task token limits, routes simple tasks to Haiku subagents (70% savings), compresses skill...

Maximise AI interaction value per token - techniques, patterns, integration with cost estimation

Token optimization — efficient reads, bash ops, model selection.

Compressed communication using symbols and abbreviations. Use when context is limited or brevity is needed.

Reduce token waste by 40-60% through anti-sycophancy rules, tool-call budgets, one-pass coding, task profiles, and read-...

Use when processing 50+ items, analyzing CSV/log files, executing code in sandbox, or searching for tools. Load for data...

Auto-injects token-efficient delegation patterns. Claude tokens are 50x more expensive than MiniMax/GLM/Kimi.

This skill should be used when creating token-efficient hook systems and MCP server architectures for web applications....

Review test cases for Token Endpoint. Covers grant_type=authorization_code, client authentication (client_secret_basic,...

A fixture with generated and non-generated non-standard content.

Token-2022 (Token Extensions) on Solana. Pick, combine and create mint and account extensions with the spl-token CLI, @s...

Systematic token definition fixes. Modifies design-tokens.yml, regenerates CSS, validates output. Handles token addition...

Convert verbose docs/markdown/text into token-efficient formats. Use when user wants to reduce token count, compress con...

Build or audit semantic design tokens in OKLCH, light and dark. Use when the user says "set up design tokens", "audit th...

Automated CSS variable injection from tokens.json. Parses design tokens → generates CSS custom properties → injects into...

Token integration and implementation analyzer based on Trail of Bits' token integration checklist. Analyzes token implem...

Comprehensive expertise in launching tokens through IDOs, implementing secure vesting contracts, designing sustainable t...

トークン管理（Token Management）機能の開発・修正を行う際に使用。Access Token, Refresh Token, ID Token, Introspection, Revocation実装時に役立つ。

Use to report how hardcoded style values on a page, file or diff map onto a project's existing design tokens, such as "a...

Automate Token Metrics tasks via Rube MCP (Composio). Always search tools first for current schemas.

Refactor the selected file(s) to minimize token usage using Conditional Flow-Style formatting. Follow these strict rules...

Minimize Claude token and cost waste across ALL surfaces — Claude Code subagents, API calls in code, and artifacts. Rout...

Standardizes design token naming patterns using hierarchical slash notation, dimension ordering, and consistent formatti...

尚书省首次调用时加载的 Token 优化策略，定义运行模式拆分、会话复用与上下文管理

CRITICAL - Read FIRST before any work. Strategies to minimize token usage and reduce costs by 60-80%.

Token优化与休眠控制集成模块 V2.1 优化点: 1. 将休眠检测(每10分钟)整合到Token监控(每6小时)，节省144次/天 ≈ 2000 token 2. 动态频率调整 - 根据Token状态自动调整监控频率 3. 分级响应...

Use BEFORE any verbose CLI run, large file read, doc conversion, or near-context handoff — decision tree keyed by intent...

Reduce token count in prompts, docs, and prose. Covers prompt compression (40-60% savings), doc formatting, TOON data se...

Reduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and nati...

Route broad repository discovery to a cheaper worker model using each client's native subagents, keeping the main agent...

Specialized logic for auditing components, detecting hardcoded values, and mapping them to the Northcote Curio design to...

Port of .claude/commands/token-plan.md for Codex.

Register and resolve multiple DynProvider instances of the same type using string tokens. Use when you need e.g. multipl...

Attribute AI usage by tokens AND dollars so a high-volume cheap model is never mistaken for the expensive one. Use when...

Token budget analytics and ROI scoring for AI agent actions. Track token cost per fix, detect wasteful loops, auto-route...

Score any crypto token using Buzz's 11-rule scoring engine. Zero LLM cost — pure rule-based analysis across liquidity, v...

4-category composite token scoring engine (11 factors, max 100) for exchange listing intelligence — evaluates market met...

Token security audit via GoPlus API

Detects user input passed to LLMs without Unicode normalization, allowing RTL overrides, zero-width joiners, and homogly...

Expert on Aptos token standards including fungible tokens (Coin, Fungible Asset), non-fungible tokens (Digital Asset sta...

Show token economics comparing usage with turbo-search vs without. Demonstrates actual savings from search-first approac...

Estimate and report token consumption after each completed step of a multi-step agent task, maintain a cumulative estima...

Execute token swaps on Uniswap/PancakeSwap across multiple EVM chains.

Track and report token usage and cost for conversations. Use when: (1) User asks about token consumption (e.g. "token用了多...

Token usage monitoring and cost tracking with configurable thresholds. Reference this skill to understand pricing and li...

Analyze Claude Code token consumption and estimated costs across projects and sessions. Use when user asks about token u...

When user says "@token-usage", "token usage", "context window", or "token cost".

Show per-session token usage breakdown. Run /token-usage or /token-usage 30 to see usage over N days.

Always-on xAI/Grok token usage and prompt-cache monitor. Syncs session context from Grok updates.jsonl, logs trends to r...

Build and share a visual dashboard for OpenClaw token usage, model cost comparison, and recent model change timeline. Us...

Token definition correctness and relationship validation. Checks token references, value formats, naming conventions, an...

Use when running the scheduled fleet token check, when asked how the quota is trending, when asked the status of the Cla...

Entry point for tokenhop — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web sea...

Chat / code generation via tokenhop using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming +...

Generate vector embeddings via tokenhop /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedd...

Generate images via tokenhop /v1/images/generations using OpenAI / Gemini Imagen / DALL-E / FLUX / MiniMax / SDWebUI / C...

Speech-to-text via tokenhop /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVID...

Text-to-speech via tokenhop /v1/audio/speech using OpenAI / ElevenLabs / Deepgram / Edge TTS / Google TTS / Hyperbolic /...

Generate videos via tokenhop /v1/videos/generations using xAI Grok Imagine (grok-imagine-video). Async job flow - submit...

Fetch URL → markdown / text / HTML via tokenhop /v1/web/fetch using Ollama Cloud / Firecrawl / Jina Reader / Tavily Extr...

Web and X search via tokenhop /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI...

Receive and verify Token.io webhooks. Use when setting up Token.io webhook handlers, debugging Ed25519 signature verific...

Use when work must model the complete transaction lifecycle and explicitly address money movement, tokenization, risk, r...