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/zgsm-ai/everything-ai-coding/claude-mdgit clone --depth 1 https://github.com/zgsm-ai/everything-ai-codingWrote 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/zgsm-ai/everything-ai-coding/claude-md)<a href="https://agentmods.dev/instructions/zgsm-ai/everything-ai-coding/claude-md"><img src="https://agentmods.dev/badge/instructions/zgsm-ai/everything-ai-coding/claude-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 5.1 | $0.12509 | $0.12509 |
| Opus 5 | $0.06254 | $0.06254 |
| Sonnet 5 | $0.02502 | $0.02502 |
| Haiku 4.5 | $0.01251 | $0.01251 |
Grade A, and why
everything-ai-coding CLAUDE.md scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**依赖说明**：sync 脚本仅用标准库（urllib、json）。评估引擎需要 `pip install -e ai-resource-eval`（pydantic、httpx）。CI 中自动安装。 How it starts
The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
项目概述
Everything AI Coding — 聚合 4000+ 精选 MCP / Skills / Rules / Prompts / Plugins 的开发资源索引。数据从 11+ 个上游源自动同步，支持 Claude Code、Opencode、Costrict、VSCode Costrict 四个平台。
提交规范
原子化提交，格式：[type] 中文描述
类型：[feat] [fix] [refactor] [docs] [ci] [chore]
规则：
- 每个提交只做一件事
- 描述用中文，简洁直白
- 不写 Co-Authored-By（除非协作场景）
测试
# 运行所有测试
python -m pytest tests/ -v
# 运行特定测试文件
python -m pytest tests/test_merge_index.py -v
python -m pytest tests/test_eval_bridge.py -v
python -m pytest tests/test_scoring_governor.py -v
开发命令
同步数据
# 同步各类型资源（需要 GITHUB_TOKEN 避免 rate limit）
GITHUB_TOKEN=xxx python scripts/sync_mcp.py
GITHUB_TOKEN=xxx python scripts/sync_mcp_registry.py # 接入 registry.modelcontextprotocol.io（active+isLatest，无需 token）
GITHUB_TOKEN=xxx python scripts/sync_rules.py
GITHUB_TOKEN=xxx python scripts/sync_windsurfrules.py # 接入 awesome-windsurfrules ×2 仓库（cross-repo dedup）
GITHUB_TOKEN=xxx python scripts/sync_skills.py # Tier 2 评估需要 LLM_* 环境变量
GITHUB_TOKEN=xxx python scripts/sync_skills_sh.py # 接入 skills.sh（mastra JSON 主路径，install_count ≥ 1000）
GITHUB_TOKEN=xxx python scripts/sync_prompts.py
# 增量抓取 mcp.so（避免全量重抓）
python scripts/crawl_mcp_so.py --mode incremental
# 合并索引（包含去重、富化、评分、生命周期管理）
python scripts/merge_index.py
# 更新 README 中的资源统计数字（中英文 README 会同时更新）
python scripts/update_readme.py
评估引擎
# 安装本地评估包（首次 / 更新后）
pip install -e ai-resource-eval
# 用 CLI 直接跑全量评估（独立于 merge 管线）
ai-resource-eval run \
--task all \
--input catalog/index.json \
--output .eval_cache/results.json \
--judge openai_compat \
--cache-dir .eval_cache \
--concurrency 5 \
--incremental \
--no-interactive \
--on-fail queue
# 环境变量：LLM_API_KEY / LLM_BASE_URL / LLM_MODEL（或 JUDGE_ 前缀）
本地验证
# 验证 JSON schema
python -c "import json; json.load(open('catalog/index.json'))"
# 检查索引完整性
python scripts/merge_index.py # 会输出去重统计和完整性警告
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.
- 6d ago First seen · 333 lines · 12,509 tokens per session scan A 73770890debd
everything-ai-coding CLAUDE.md is an instructions file published in the GitHub repository zgsm-ai/everything-ai-coding (204 stars, last pushed 5d ago), licensed MIT. It adds 12,509 tokens to every session, about $0.0625 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
AmbyKit CLAUDE.md
Claude Code instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.
sugar AGENTS.md
AGENTS.md instructions for roboticforce/sugar, covering sugar - agents.md, git branching rules (strict), always create branches from develop, after work is complete and then create pr targeting develop.
nextjs-skills CLAUDE.md
Instructions for mohamed-hossam1/nextjs-skills: All contribution rules — style, naming, file layout, verification — live in AGENTS.md. Read that first.
humanfile copilot-instructions.md
Instructions for zhangyu94/humanfile, covering .human file boundaries, rules and behavior.
Fireteam AGENTS.md
Instructions for martinnaithani/Fireteam, covering agent instructions for maintaining fireteam, what this repo is, critical constraints, file structure and naming conventions (do not change).