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/raphaelmansuy/edgecrab/agents-mdgit clone --depth 1 https://github.com/raphaelmansuy/edgecrabWhat 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 | $0.09503 | $0.09503 |
| Opus 5 | $0.04751 | $0.04751 |
| Sonnet 5 | $0.01901 | $0.01901 |
| Haiku 4.5 | $0.00950 | $0.00950 |
Grade A, and why
edgecrab 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 2d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 2d ago First seen · 795 lines · 9,503 tokens per session scan A a90c7d53d614
edgecrab AGENTS.md is an instructions file published in the GitHub repository raphaelmansuy/edgecrab (84 stars, last pushed 1mo ago), with no licence file. It adds 9,503 tokens to every session, about $0.0475 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
GENesis-AGI AGENTS.md
AGENTS.md instructions for WingedGuardian/GENesis-AGI, covering agent instructions, code review mandate (adversarial), gitnexus — code intelligence (advisory), genesis capability surface and skills.
GENesis-AGI CLAUDE.md
Claude Code instructions for WingedGuardian/GENesis-AGI, covering genesis v3 — project instructions, architecture, environment, process management and common commands.
lihongwei-cn CLAUDE.md
Instructions for LiHongwei-cn/lihongwei-cn, covering claude.md — claude code 项目记忆, 用户身份, 回复风格（红线）, 网站 and 技术栈.
lihongwei-cn copilot-instructions.md
Instructions for LiHongwei-cn/lihongwei-cn: 1|# Universal Agent Spec — 通用规范核心 2| 3|> 本文件是所有 AI Agent 共享的行为规范。 4|> 各 Agent 适配文件（agents/ 目录）在部署时会把本文件内容与 Agent 专属配置合并。 5|> 修改本文件 = 修改所有 Agent 的行为。 6| 7|## 语言规则 8| 9|始终使用中文（简体中文）回复。 10| 11|仅以下内容使用英文： 12|- 代码本身（变量名、函数名、类名、关键字） 13|- URL 链接、命令行指令、API Key 14|…
headless-agentic-codebase CLAUDE.md
Instructions for nkhdiscovery/headless-agentic-codebase, covering what {{projectname}} is, your authority, architecture invariants (challenge via adr, not silently), coding conventions and unattended mode.
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.