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/komagon/hermes-production-patterns/agents-mdgit clone --depth 1 https://github.com/Komagon/hermes-production-patternsWrote 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/komagon/hermes-production-patterns/agents-md)<a href="https://agentmods.dev/instructions/komagon/hermes-production-patterns/agents-md"><img src="https://agentmods.dev/badge/instructions/komagon/hermes-production-patterns/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 | $0.00795 | $0.00795 |
| Opus 5 | $0.00398 | $0.00398 |
| Sonnet 5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
hermes-production-patterns 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.
What it actually says
Hermes Production Patterns
项目概述
此仓库包含一套生产级的 Hermes Agent 工程模式、公约和模板。目标是帮助开发者从「手写提示词」进化到「设计自主运行的 Agent 系统」。
核心能力
| 能力 | 入口点 |
|---|---|
| Maker/Checker 分离 | conventions/maker-checker.md |
| 状态文件管理 | conventions/state-file-pattern.md |
| 控制流分离 | conventions/control-flow-separation.md |
| 错误压缩与自愈 | conventions/error-compact-pattern.md |
| 技能进化 | conventions/skill-evolution.md |
| Cron 任务设计 | conventions/cron-job-pattern.md |
| 检查点恢复 | conventions/checkpoint-pattern.md |
| 密钥管理 | conventions/secret-management.md |
| 数据驱动技能优化 | conventions/data-driven-optimization.md |
| 💡 反面模式 | conventions/anti-patterns.md |
| 🧩 模式组合指南 | conventions/pattern-composition.md |
| 📐 状态文件 Schema | conventions/state-schema.json |
| 🔄 自更新安全流程 | conventions/self-update-pattern.md |
| 🧠 认知记忆系统 | conventions/memory-os-pattern.md |
| 📈 进化闸门 | conventions/evolution-gate.md |
| 回归反测集 | test-prompts.json(25 条,含 assertions/forbidden) |
| 模板 | templates/ |
| 设计模式 | patterns/ |
| 实战示例 | examples/ |
| 公众号文章流水线 | examples/wechat-article-pipeline.md |
| 🚀 Starter Kits(6 个可复制骨架) | starter-kits/(入口 starter-kits/index.md) |
| 🚀 Production Stacks(5 个官方组合) | stacks/(入口 stacks/index.md) |
| 🚀 10-Minute Quick Start | quickstart.md |
| 🚀 Production Recipes(7 个完整方案) | recipes/(入口 recipes/index.md) |
| 🚀 Production Audit + Readiness Score | audit/audit.md |
| 🚀 兼容性矩阵 | compatibility/README.md |
| 🚀 hpp CLI(init/add/validate/audit/doctor) | cli/hpp.py |
你的角色
- 新用户路径:读
quickstart.md→ 复制 starter-kit → 按验证清单跑通 - 阅读
conventions/理解工程模式 — 这些是可执行的技能文件 - 阅读
patterns/理解方法论 — 这些是设计决策的上下文 - 使用
templates/快速起步 — 填空即用 - 选场景方案 — 先看
stacks/组合,再看recipes/完整方案 - 验收项目 —
cli/hpp audit出五维得分,audit/checks/checklist.md逐项核对
约束
- 不要修改
conventions/文件的内容来绕过设计意图 - 所有 Cron 任务必须经过 L1→L2→L3 成熟度分级
- Maker 和 Checker 必须是独立的 Agent 实例
- 错误信息必须压缩后写入上下文
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 · +10 lines · +241 tokens per session 08ebee8d7b20
- 4d ago First seen · 44 lines · 554 tokens per session scan A 656a22c963f4
hermes-production-patterns AGENTS.md is an instructions file published in the GitHub repository Komagon/hermes-production-patterns (14 stars, last pushed yesterday), licensed MIT. It adds 795 tokens to every session, about $0.0040 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
gomaa CLAUDE.md
Claude Code instructions for M4F-S/gomaa, covering 🎯 agent operational directives & execution protocol, role & objective, core rules and execution protocol.
portable-agent-skills AGENTS.md
Instructions for ch1109/portable-agent-skills: Read CONTRIBUTING.md before changing a Skill.
mumei CLAUDE.md
Instructions for iroha924/mumei, covering mumei development guide, what mumei is, language policy, bash + jq conventions (essentials) and schemas/ conventions (essentials).
octowiz CLAUDE.md
Instructions for raelli/octowiz, covering octowiz, releasing & deploying, commands, agent skills and issue tracker.
pm-workflow-plugin CLAUDE.md
Instructions for derricktang/pm-workflow-plugin, covering claude.md, 项目性质, 斜杠命令, 目录结构 and 工作流架构.
marketplace-mcp AGENTS.md
AGENTS.md instructions for YegorMy/marketplace-mcp, covering agent notes, rules and verification.