Burn Token
Use when user wants to burn tokens aggressively - infinite loop of analysis, summarization, or heavy math computation. Maximizes token consumption by defeating KV cache, randomizing prompts, and dispatching verbose subagents. Supports time limits, round limits, or unlimited burn until interrupted.
Install
npx skills add shengxinjing/burn-token --skill burn-tokengit clone --depth 1 https://github.com/shengxinjing/burn-token.git /tmp/burn-token
mkdir -p ~/.claude/skills
cp -r /tmp/burn-token/skill ~/.claude/skills/burn-tokenPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Burn Token Relentlessly consume tokens through an infinite loop of heavyweight computation. Designed to burn through even unlimited plans by maximizing output tokens per task, defeating KV cache with entropy injection, and never stopping unless told to. ## Arguments `/burn-token [duration] [mode] [name]` | Argument | Format | Default | Example | |----------|--------|---------|---------| | duration | `30m`, `1h`, `2h30m`, `forever` | `forever` | `/burn-token 1h` | | rounds | `N rounds` | unlimited | `/burn-token 50 rounds` | | mode | `code`, `math`, `bless` | `bless` | `/burn-token 1h math` | | name | any string (bless mode only) | `众生` | `/burn-token bless dasheng` | Examples: - `/burn-token` — infinite bless burn (default mode), 为众生念经 - `/burn-token bless dasheng` — 为 dasheng 念经祈福,烧 token 直到烧完 - `/burn-token 2h bless 大圣` — burn for 2 hours blessing 大圣 - `/burn-token 2h` — burn for 2 hours - `/burn-token 100 rounds` — burn for 100 rounds - `/burn-token forever math` — infinite math burn - `/burn-token 4h code` — 4-hour code analysis burn ## Scheduling For recurring burns: ``` /loop 1h /burn-token 45m /schedule create --cron "0 */2 * * *" --prompt "/burn-token 1h45m" /schedule create --cron "0 0 * * *" --prompt "/burn-token 8h" ``` ## CRITICAL: KV Cache Defeat Strategy KV cache reuse drastically reduces token consumption. Every subagent prompt MUST include entropy to ensure cache misses:
Details
- Skill name
burn-token- Repository
- shengxinjing/burn-token
- Path
skill/SKILL.md- License
- MIT
- Repo updated
- 5 April 2026
FAQ
What does the Burn Token skill do?
Use when user wants to burn tokens aggressively - infinite loop of analysis, summarization, or heavy math computation. Maximizes token consumption by defeating KV cache, randomizing prompts, and dispatching verbose subagents. Supports time limits, round limits, or unlimited burn until interrupted.
How do I install the Burn Token skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add shengxinjing/burn-token --skill burn-token. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Burn Token popular?
It lives in shengxinjing/burn-token, which has 43 GitHub stars and 1 forks.
Related skills
Datahub Evals
46datahub-project/datahub-skills
Use this skill to run DataHub's saved evals and report answers for judging. Triggers on: "run our evals", "run the eval suite", "run eval urn:li:eval:...", "how are our evals doing", "check for eval regressions", "upload this answer as an eval result", "score this answer with the DataHub judge", "compare two agents on the same eval". Answers each eval in a fresh agent with the DataHub tools attached, reports the answer through the DataHub Cloud CLI, and reads back the verdict DataHub's own judge produced.
Booking Best Price
34aiwithremy/claude-skills-booking-best-price
Use when the user pastes a holiday-rental or hotel listing link (Airbnb, Stayz, Vrbo, Expedia, Booking.com, HomeToGo, or similar) and wants to identify the actual property, find it listed on other sites, compare prices to book it cheaper, or track down the property manager / owner contact to book direct. Requires the Firecrawl MCP server. This skill verifies Firecrawl is installed and walks the user through setup first if it is not.
Vibe Upskill
43bb-cccc/vibe-upskill
Extract coding knowledge from agent-assisted development sessions and convert them into interview-ready scenario Q&A cards and structured knowledge base documents. Use when the user wants to learn from their vibe coding history, prepare for technical interviews, build a personal knowledge base from agent workflows, review what an agent did during coding/debugging/deployment, or transform agent conversations into personal skills. Triggers: "vibe coding", "agent record", "knowledge extraction", "interview prep", "scenario questions", "what did the agent do", "learn from agent", "coding knowledge
Agent Builder
49vitoworleone/claude-code-handbook
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code, Cursor, or similar agent internals (5) want to build agents for business, research, creative, or operational tasks Keywords: agent, assistant, autonomous, workflow, tool use, multi-step, orchestration
Web Navigator
43Plocr/Reasonix-computer-use
Web 浏览器自动化路由规则。通过 web_navigator 将 Web 场景路由到 Playwright MCP 或 mcp-chrome。
Lark MCP
37whatevertogo/FeiShuSkill
飞书/Lark 官方 MCP 集成。支持发送消息、创建群组、操作多维表格(Bitable)、导入/搜索文档、知识库查询。触发词:飞书、Feishu、Lark、多维表格、bitable、飞书文档、飞书群。
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.