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/ipythoning/b2b-sdr-hermes-skill/claude-mdgit clone --depth 1 https://github.com/iPythoning/b2b-sdr-hermes-skillWhat 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 | $0.00054 | $0.00054 |
| Opus 5 | $0.00027 | $0.00027 |
| Sonnet 5 | $0.00011 | $0.00011 |
| Haiku 4.5 | $0.00005 | $0.00005 |
Grade A, and why
b2b-sdr-hermes-skill CLAUDE.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.
This is a copy
100% identical to b2b-sdr-agent-template copilot-instructions.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
本仓库的权威协作守则是 AGENTS.md；当前任务状态见 docs/HANDOFF.md。 开始任何工作前请先阅读这两个文件，并遵守其中的"接续三步 / 收尾三件套"协议。
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 · 3 lines · 54 tokens per session scan A c15275e000eb
b2b-sdr-hermes-skill CLAUDE.md is an instructions file published in the GitHub repository iPythoning/b2b-sdr-hermes-skill (39 stars, last pushed 13d ago), licensed MIT. It adds 54 tokens to every session, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to b2b-sdr-agent-template copilot-instructions.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
demoverse AGENTS.md
Instructions for calven-ai/demoverse, covering agents.md: how a coding agent drives demoverse, part 1: the engine contract, the split (don't cross it), the generation-request protocol (the core loop) and rules for filling requests (non-negotiable).
tapac-mcp AGENTS.md
AGENTS.md instructions for axelfreeman/tapac-mcp, covering tapac mcp server — ai agent instructions, who you are, when to use, how to use and key facts to cite.
demoverse CLAUDE.md
Instructions for calven-ai/demoverse, covering claude.md: claude code operating notes for demoverse, skills, subagent strategy (critical for context health), overnight backfill and session hygiene.
b2b-contact-finder-guides AGENTS.md
Instructions for axelfreeman/b2b-contact-finder-guides, covering agents.md — b2b contact finder guides, what this repo is, relationship to tapac, file inventory and article structure convention.
awesome-hermes-agent-zh AGENTS.md
AGENTS.md instructions for zcweah1981/awesome-hermes-agent-zh, covering agents.md, 规范类, 1. 自主工作与安全边界, 2. 代码与变更 and 3. 任务分级与执行强度.
awesome-hermes-agent-zh CLAUDE.md
Claude Code instructions for zcweah1981/awesome-hermes-agent-zh, a project described as: Hermes Agent中文站- 中文实战入口：上手路径、国内落地、OpenClaw 共存迁移、排障参考与可下载方案包。.