一键导入
light-mode
Guidelines for fast-tracking trivial tasks (typos, UI tweaks, simple bugfixes).
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。
菜单
Guidelines for fast-tracking trivial tasks (typos, UI tweaks, simple bugfixes).
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
| name | light-mode |
| description | Guidelines for fast-tracking trivial tasks (typos, UI tweaks, simple bugfixes). |
| tier | 2 |
| triggers | ["/light workflow","[LIGHT] tag in TASK.md"] |
| version | 1 |
Tier: 2 (Load on specific trigger) Purpose: Provide streamlined instructions for trivial, low-risk tasks.
A task qualifies for Light Mode if ALL of the following are true:
auth*, payment*, crypto*, security*.If ANY condition is false, ESCALATE to standard pipeline.
[LIGHT] tag.skill-security-audit.If at any point the task complexity exceeds Light Mode scope:
/01-start-feature instead.[LIGHT] tag should be removed from the TASK.The following files are PROHIBITED from Light Mode modifications:
**/auth/**, **/authentication/****/payment/**, **/billing/****/crypto/**, **/encryption/****/security/**.env, *.pem, *.keyIf the task touches these files, ALWAYS escalate to standard pipeline with Security Audit.
Use when decomposing tasks into parallel sub-tasks or spawning sub-agents. Vendor-agnostic core; load a per-vendor reference for concrete tool names, directory conventions, and invocation syntax.
Use when performing Verification-Driven Development with adversarial approach. Actively challenge assumptions and find weak spots.
Use when performing VDD adversarial review with an opt-in sarcastic, provocative delivery style — a stylistic skin over vdd-adversarial mechanics (exhaustive reporting + objective bar).
Performance critic in adversarial style (optional sarcastic skin). Part of VDD Multi-Adversarial pipeline.
Use when performing OWASP security critique in adversarial style (optional sarcastic skin). Part of VDD Multi-Adversarial pipeline.
Use when performing security vulnerability assessment (OWASP, secrets, dependencies, IaC, LLM, API, MCP/agentic) or when "thinking like a hacker" to find exploits.