Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
wu529778790 avatar

Token Burner

  • 396 installs
  • Updated June 24, 2026
  • wu529778790/shenzjd-skills

Helps with ai & agent building tasks.

About

token-burner is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.

  • token-burner
  • AI & Agent Building
  • AI-coding skill

Token Burner by the numbers

  • 396 all-time installs (skills.sh)
  • +60 installs in the week ending Jul 27, 2026 (Skillselion tracking)
  • Ranked #1,984 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
  • Data as of Jul 27, 2026 (Skillselion catalog sync)
npx skills add https://github.com/wu529778790/shenzjd-skills --skill token-burner

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs396
Last updatedJune 24, 2026
Repositorywu529778790/shenzjd-skills

What it does

Helps with ai & agent building tasks.

Files

SKILL.mdMarkdownGitHub ↗

Token Burner

在 token 过期前自动执行有价值的项目改进任务,不浪费任何额度。

Overview

自动扫描项目,发现代码审查、测试生成、文档完善、依赖审计、重构等任务,按优先级排序后自主执行。使用 worktree 隔离每个任务,执行后自动验证,确保每次修改都是安全的。

When to Use

  • User wants to use tokens productively before they expire
  • User wants to run an autonomous code improvement session
  • User says "burn tokens" / "token burner" / "用掉 token"
  • User wants to auto-discover and fix issues across a project
  • User inputs /token-burner
  • User wants automated code review across the project
  • User wants to find and fix code smells automatically
  • User wants to improve test coverage without manual effort
  • User wants to do a full project health check and cleanup

When NOT to Use:

  • User wants to work on a specific, well-defined task (use normal workflow)
  • User wants to chat or brainstorm (no token waste concern)
  • User's project has no code to improve
  • User wants to run automated tests only (use test runner directly)
  • User wants to generate documentation only (use doc generation tools)
  • User wants to refactor specific files (do it manually for better control)

Core Pattern

Step 1: 项目扫描

检测项目类型和结构,发现可执行任务:

# 检测项目类型
test -f package.json && echo "Node.js"
test -f go.mod && echo "Go"
test -f requirements.txt && echo "Python"
test -f Cargo.toml && echo "Rust"

# 检测 git 状态
git log --oneline -5          # 最近变更
git diff --stat HEAD~3        # 变更范围
git status --porcelain        # 未提交变更

任务发现引擎:(详见 templates/task-discovery.md

任务类型发现方式优先级
🔒 依赖安全如果 dependency-audit skill 可用则委派,否则直接运行审计工具P0 - 立即执行
🐛 代码缺陷分析 git diff 中的逻辑问题P0 - 立即执行
🧪 测试覆盖找无测试的源文件,检查覆盖率P1 - 高优先级
📝 文档缺失检查 README、函数注释、API 文档P2 - 中优先级
♻️ 代码重构重复代码、复杂函数、code smellP2 - 中优先级
🧹 Git 清理过时分支、conflict markers、大文件P3 - 低优先级

生成任务列表,每个任务包含:typefiledescriptionimpact(high/medium/low)、risk(high/medium/low)。

Step 2: 优先级排序

score = impact_score × (1 - risk_score) 排序:

因子highmediumlow
impact321
risk0.80.40.1

安全策略:

  • P0 任务(安全漏洞、缺陷)→ 立即执行
  • P1 任务(测试)→ 可以执行,但每个任务在 worktree 中隔离
  • P2 任务(文档、重构)→ 可以执行
  • P3 任务(清理)→ 只在有剩余 token 时执行

前置依赖检查:

执行前先检查所需工具是否可用,缺失时跳过对应任务类型而非静默失败:

# 检查工具可用性
command -v jq >/dev/null 2>&1 || echo "⚠️ jq 未安装,安全审计任务将跳过"
command -v npm >/dev/null 2>&1 || echo "⚠️ npm 未安装,Node.js 审计将跳过"
command -v go >/dev/null 2>&1 || echo "⚠️ go 未安装,Go 审计将跳过"
command -v pip-audit >/dev/null 2>&1 || echo "⚠️ pip-audit 未安装,Python 审计将跳过"

过滤规则:

  • 跳过 node_modules/vendor/.git/ 等目录
  • 跳过已由其他 skill 覆盖的任务(如 git-hooks-setup 已配置的)
  • 跳过超过 500 行变更的大任务(拆分为子任务)

Step 3: 自主执行

使用 Agent tool 逐个执行任务,每个任务在独立 worktree 中:

对每个 task in 队列:
  retries = 0
  max_retries = 3
  while retries < max_retries:
    1. Agent(task.prompt, {
         subagent_type: "general-purpose",
         isolation: "worktree",
         description: "token-burner:" + task.type
       })
    2. 在 worktree 中跑测试验证
    3. 如果测试通过 → 合并到主分支,break
    4. 如果测试失败 → retries++
       - 如果 retries < max_retries → 回滚 worktree,重试
       - 如果 retries >= max_retries → 记录失败原因,跳过此任务
    5. 更新任务状态

每种任务的执行策略:

任务类型执行方式验证方式
🔒 依赖安全运行审计工具,生成修复命令重新审计确认
🐛 代码缺陷分析 diff,定位问题,修复跑相关测试
🧪 测试覆盖为源文件生成单元测试跑新测试确认通过
📝 文档缺失生成 README/注释/API docs检查文档格式
♻️ 代码重构提取函数、消除重复、简化逻辑跑全量测试
🧹 Git 清理清理无用文件、格式化git status 确认

执行限制:

  • 每个任务最多 3 次重试
  • 单个任务超时 5 分钟则跳过
  • 总任务数默认最多 20 个(可通过 --max-tasks 调整)

Step 4: 记录和报告

每个任务完成后记录到 memory(任务类型、文件、状态、说明),执行结构见 templates/execution-report.md

Step 5: 收尾

生成最终报告 templates/execution-report.md,包含:

  • 执行统计(成功率、耗时、token 消耗估算)
  • 每个任务的详细结果
  • 未执行任务的原因
  • 下次运行建议

Quick Reference

Note: Parameters below are natural language hints parsed by the AI. Without parameters, the AI will ask interactively.

/token-burner                          # Scan and execute all tasks
/token-burner 只跑测试和文档            # Only test and doc tasks
/token-burner 最多跑 10 个任务          # Limit to 10 tasks
/token-burner 只扫描不执行              # Scan only, don't execute
/token-burner 扫描 /path/to/repo       # Target specific project
HintDescriptionDefault
只跑 typeTask type filter (security/bug/test/docs/refactor/clean)All
最多跑 N 个任务Maximum tasks to execute20
只扫描不执行Scan only, don't executefalse
扫描 pathTarget project pathCurrent directory

Common Mistakes

错误正确做法原因
不跑测试就合并每个任务执行后必须验证避免引入新 bug
一次执行太多任务控制在 20 个以内避免 token 耗尽时半途而废
跳过 worktree 隔离始终用 isolation: "worktree"避免任务间互相干扰
不记录执行结果写入 memory 文件下次运行需要知道哪些做过
对生产代码不做验证改完必须跑测试确保不破坏现有功能
不检查工具可用性执行前验证工具是否存在缺失工具的任务应跳过而非报错
在大项目上不限制任务数设置 --max-tasks 限制避免 token 耗尽后任务中断
跳过风险评估按 impact × (1 - risk) 排序高风险任务应谨慎处理
不区分 node_modules 等目录跳过 vendor/node_modules/.git扫描第三方代码浪费 token
重构时不做 diff 检查限制单任务变更 < 500 行过大变更难以验证安全性

Related skills

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.