Borrowing it
Nothing to install: this file belongs to Light0305/Light-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Light0305/Light-skills/master/AGENTS.mdgit clone --depth 1 https://github.com/Light0305/Light-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/light0305/light-skills/agents-md)<a href="https://agentmods.dev/instructions/light0305/light-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/light0305/light-skills/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/light0305/light-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/light0305/light-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00548 | $0.00548 |
| Opus 5.5 | $0.00219 | $0.00219 |
| Sonnet 5.5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
Light-skills AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Light-Skills 代理协作说明
本仓库是公开科研全流程技能包，面向 Claude Code / Codex / OpenCode。请把 skills/ 视为唯一 canonical 技能源；不要把维护者私人记忆、对话史、邮箱、未公开研究、db01-db09、MCP 配置或本地知识库内容写进仓库。
客户端发现路径
三类客户端默认发现路径不同。项目级使用前先运行：
$env:PYTHONUTF8="1"
python scripts\bootstrap_agent_skills.py --mode auto --force
该脚本把 skills/ 安全映射到：
.agents/skills：Codex / OpenCode open-standard 项目技能路径。.claude/skills：Claude Code 项目技能路径，也可被 OpenCode 读取。.opencode/skills：OpenCode 原生项目技能路径。
Windows 不能创建目录 symlink 时，脚本会回退为 copy，并写入 .light_generated_link 标记；修改 canonical skills/ 后需重新运行 --force 刷新生成副本。脚本不会覆盖没有 Light 生成标记的用户目录。
开发纪律
- commit 只署作者本人；标题和正文写中文；不要添加 Co-Authored-By。
- 不要 push，除非用户明确要求。
- Python 命令前设置
PYTHONUTF8=1；临时产物放.upgrade/_e2e。 - 用户面向脚本必须亲手跑
--selftest到 exit 0，不能相信“已完成”报告。 - 动态事实、论文、DOI、star、链接、能力声明查不到就写
unknown/待核查。 - 论文数据图必须程序化生成；禁止 AI 生图冒充数据图。
- R/ggplot2 是增强路径，不是静默前提：缺 R 或缺包时，先给用户“继续 matplotlib 诚实降级 / 安装或配置 R / 提供 Rscript 路径”的选择；非交互自动流程默认降级并标
degraded=True，不得擅自安装。
快速自测
$env:PYTHONUTF8="1"
python scripts\bootstrap_agent_skills.py --selftest
python scripts\bootstrap_agent_skills.py --check-only
python skills\light-figure\scripts\r_ggplot.py --selftest
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 40 lines · 548 tokens per session scan A 2312d0eff162
Light-skills AGENTS.md is an instructions file published in the GitHub repository Light0305/Light-skills (791 stars, last pushed 3mo ago), licensed MIT. It adds 548 tokens to every session, about $0.0022 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.