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 skills/komagon/hermes-production-patterns/basic-agentnpx skills add Komagon/hermes-production-patterns --skill basic-agentgit 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.
![agentmods badge for [object Object]](/badge/skills/komagon/hermes-production-patterns/basic-agent.svg?v=0-11-A){kind=icon}
[](https://agentmods.dev/skills/komagon/hermes-production-patterns/basic-agent)<a href="https://agentmods.dev/skills/komagon/hermes-production-patterns/basic-agent"><img src="https://agentmods.dev/badge/skills/komagon/hermes-production-patterns/basic-agent.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 | $0.00011 | $0.00229 |
| Opus 5 | $0.00005 | $0.00114 |
| Sonnet 5 | $0.00002 | $0.00046 |
| Haiku 4.5 | $0.00001 | $0.00023 |
Grade A, and why
[object Object] 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
{My Skill}
简明扼要的技能说明
核心逻辑
1. 输入处理
{描述需要什么输入,从哪里获取}
2. 执行
{具体执行步骤,按序编号;确定性步骤标注 script 交给脚本}
3. 验证
{如何验证输出质量,输出是否满足输入要求}
状态契约(STATE.md)
- 读取:每次运行先读 STATE.md 的 Progress/Last run
- 写入:每完成一步写回进度与结果摘要
陷阱
- 用 LLM 心算确定性计算 → 写脚本
- 跑完不写 STATE.md → 断点丢失
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 38 lines · 11 tokens per session scan A 0fa732d5b7f4
[object Object] is a skill published in the GitHub repository Komagon/hermes-production-patterns (14 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 229 once invoked, about $0.0001 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 2026-09-04.
Other skills, from other repositories
comet-verify
Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.
comet-design
Comet Classic 阶段 2 —— 为 change 产出深度技术 Design Doc。.
generate-harness-dsl
Generate, revise, or review complete Harness as Code .harness files when a coding-agent workflow, agent role, skill, tool contract, MCP connection, runtime, or deployment must be compiler-valid and resolvable with @qoder-ai/harness.
cache-attack
Poison CDN cache or deceive when X-Cache header is detected.
subdomain-enumeration
Map subdomains via crt.sh and subfinder at recon kickoff.
create-task
Create an end-to-end Continual Learning Bench task. Use when adding a new src/tasks/ benchmark task, including design interview, concrete Jinja prompt templates, JSON action contracts, observation templates, debug schedule, behavioral E2E tests, validation, smoke/debug runs with icl and iclnotepad, and README…