Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/huangwb8/skills/agents-mdgit clone --depth 1 https://github.com/huangwb8/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/huangwb8/skills/agents-md)<a href="https://agentmods.dev/instructions/huangwb8/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/huangwb8/skills/agents-md.svg" alt="Measured on agentmods" 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 | $0.10019 | $0.10019 |
| Opus 5 | $0.05010 | $0.05010 |
| Sonnet 5 | $0.02004 | $0.02004 |
| Haiku 4.5 | $0.01002 | $0.01002 |
Grade A, and why
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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skills - 项目指令
本项目是 Agent Skills 开发流水线：用于创建、优化和维护高质量、可复用的 AI Agent Skills。所有技能遵循 Agent Skills 开放标准，确保在 Claude Code、OpenAI Codex、Cursor 等多个平台间"编写一次，随处使用"。
核心价值：
- 提供标准化的技能开发框架和工作流
- 确保技能质量（安全性、可靠性、通用性）
- 支持有机迭代和持续优化
兼容平台：Claude Code、OpenAI Codex、Cursor、GitHub、VS Code、Amp、Letta、Goose（详见 Agent Skills 官方网站）。
目录结构与边界
skills/alpha/<skill-name>/：可发布、默认安装的成熟 Skill；以自身SKILL.md为识别边界，可包含专属的scripts/、references/、templates/和资源文件。skills/beta/<skill-name>/：尚未成熟的候选 Skill；不进入默认安装源，仅当用户显式指定 beta 源目录时才处理。skills/alpha/auto-draw-plot/：该 Skill 属于 Sub2API 生态，在 Sub2API 源仓库的skills/auto-draw-plot/协同开发。本项目不承担其功能开发、测试计划或日常维护，仅托管从外部开发源同步的最新可发布源代码，供公开发布与安装发现；发现问题时应回到 Sub2API 源仓库处理后再同步。packages/<project>/：独立运行时包边界，拥有自己的项目配置、版本、依赖和测试；不得在包内放置领域 Skill 流程。docs/plans/：正式计划、迁移说明和治理文档；不得在 Skill 目录内新建plans/。tests/：面向packages/Python 包核心公开 API 及仓库级公开入口（如安装器）的可执行 smoke/integration 测试脚本；不承载测试计划、报告、artifacts、fixture 或运行缓存。tmp/：测试脚本运行过程的临时承载目录，可包含测试计划、报告、artifacts、fixture 和日志；Python/pytest/Ruff 等运行缓存统一写入.bensz-api/，不得回写到tests/或tmp/。./.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/：本轮任务的输入、过程产物、日志和验证证据；正式交付物不写入其中。
目录职责规则：
- 包内单元测试放在对应
packages/<project>/tests/；跨包或仓库公开入口测试脚本放在根级tests/；测试运行产物统一写入根级tmp/。 - Skill 目录内不得新建历史计划、测试夹具或运行缓存目录。
- AI 任务级中间材料遵循下方
.bensz-api工作区协议。
Python 与工具运行产物归档
本仓库的标准开发与完整运行环境统一为 Python 3.11+；本地完整安装器和 bensz-skill-kernel 均不得声明或暗示支持更低版本。skills/alpha/install-bensz-skills/scripts/bootstrap_install.py 是唯一例外：它作为只依赖标准库的首次/应急远程引导入口，最低支持 Python 3.8，但这一兼容范围不扩展到本地完整安装器、Kernel 或仓库开发流程。Python 3.8–3.10 环境只能使用 bootstrap 安装生产 Skill；需要本地源码安装、开发或 Kernel 时必须升级到 Python 3.11+。
- Python、pytest、Ruff、mypy、coverage、tox/nox、构建工具和新建/临时虚拟环境产生的运行产物必须集中放在当前项目的
.bensz-api/下，不得在仓库根目录或packages/<project>/留下同类目录。 - 重点包括但不限于：
.ruff_cache/、.pytest_cache/、.mypy_cache/、__pycache__/、.tox/、.nox/、.coverage、coverage.xml、htmlcov/、*.egg-info/、临时build//dist/、.venv/和venv/。其中可复用的正式构建交付物仍按项目发布约定保存；已有且可能被用户维护的虚拟环境不得未经确认直接迁移，后续新环境统一使用.bensz-api/.venv。 - 仓库级 pytest 使用
.bensz-api/.pytest_cache；Ruff 使用.bensz-api/.ruff_cache；包级配置不得回退到packages/<project>/.pytest_cache或packages/<project>/.ruff_cache。 - 脚本不得把上述路径硬编码到源码树；优先从项目根目录推导
.bensz-api，通过工具原生配置或子进程环境变量（如RUFF_CACHE_DIR、PYTHONPYCACHEPREFIX）指定路径，并允许用户显式环境变量覆盖。 - 已有历史缓存可安全清理或迁移；验证时应检查运行前后仓库源码目录没有新生成的缓存目录。
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.
- today Changed · +49 lines · +1,389 tokens per session 084b2d9d35c6
- yesterday Changed · +11 lines · +387 tokens per session 644710dd1074
- 5d ago First seen · 340 lines · 8,243 tokens per session scan A 5fbc2c744ab1
skills AGENTS.md is an instructions file published in the GitHub repository huangwb8/skills (48 stars, last pushed today), licensed MIT. It adds 10,019 tokens to every session, about $0.0501 per session on Opus 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
AI-Rig CLAUDE.md
Claude Code instructions for Borda/AI-Rig, covering instruction layering, edit scope — hard constraint, lint/format — use pre-commit hooks, not direct tools, test workflow and python documentation style.
supergraph AGENTS.md
AGENTS.md instructions for datit309/supergraph, covering supergraph — mandatory workflows, skills, auto language detection, tiered workflow — pick the right tier first and full pipeline (tier 3).
mobile-ai-agents CLAUDE.md
Claude Code instructions for salmanashraf/mobile-ai-agents, covering claude.md — mobile ai agents, what this repo is, quick start, install everything and install by platform.
MemoryCustodian GEMINI.md
Gemini CLI instructions for waittim/MemoryCustodian, covering agent instructions, memorycustodian and development.
dining-places-skill AGENTS.md
AGENTS.md instructions for ddalgrande/dining-places-skill, covering agents.md, how to use it, by agent capability, the one command and ground rules.
idd-skill idd-resume.instructions.md
Instructions for kurone-kito/idd-skill, covering idd — resume phase, required inputs, step 0 — route classifier, operator-present release and step 1 — identify claim state.