菜单
Token-aware wrappers around build, test, lint, and format commands to prevent context window overflow. Centralizes command execution through scripts that truncate noisy logs while preserving actionable error information.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Enhance session checkpoints with git context and diff summaries. Use after completing significant work to enrich checkpoint.md files with repository state, recent commits, and code change summaries. Triggers include "enhance checkpoint", "update checkpoint with git", "add git context to checkpoint", or when finishing a multi-file change session.
Use for model training, hyperparameter tuning, and Modal GPU training.
Use when invoking training, evaluation, and dataset preparation via CLI. Provides all standard commands for this project.
Multi-perspective code analysis using three AI personas (RYAN, FLASH, SOCRATES) for comprehensive decision-making. Use when complex code decisions need analysis from multiple viewpoints, or when avoiding single-perspective blind spots is critical.
Use for authentication management, token validation, and credential troubleshooting.
Use for secrets management, credentials handling, and security best practices.
| name | token-reducer |
| description | Token-aware wrappers around build, test, lint, and format commands to prevent context window overflow. Centralizes command execution through scripts that truncate noisy logs while preserving actionable error information. |
This skill provides token-aware wrappers around build, test, lint, and format commands to prevent context window overflow in Claude Code and similar agents. It centralizes command execution through scripts that truncate noisy logs while preserving actionable error information.
../token_safe_exec.sh - Bash wrapper for any build/test command../smart_lint.py - Python wrapper for lint/format commands with error-focused filteringInstead of running raw commands like:
cargo testnpm testpytestgo test ./...Always run:
bash .agents/skills/token_safe_exec.sh "<your_command_here>"
Examples:
bash .agents/skills/token_safe_exec.sh "cargo test --all --quiet"
bash .agents/skills/token_safe_exec.sh "npm test"
bash .agents/skills/token_safe_exec.sh "pytest -q"
Instead of:
eslint .flake8 .ruff check .black .Use:
python .agents/skills/smart_lint.py "<your_command_here>"
Examples:
python .agents/skills/smart_lint.py "eslint . --max-warnings=0"
python .agents/skills/smart_lint.py "ruff check ."
python .agents/skills/smart_lint.py "flake8 ."
Agents working in this repository must follow these rules:
cargo test, npm test, pytest, go test, or similar commands directly.eslint ., ruff check ., flake8 ., black .).bash .agents/skills/token_safe_exec.sh "<command>".python .agents/skills/smart_lint.py "<command>".