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/lipu-jpg/openwrite/agents-mdgit clone --depth 1 https://github.com/LiPu-jpg/OpenwriteWrote 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/lipu-jpg/openwrite/agents-md)<a href="https://agentmods.dev/instructions/lipu-jpg/openwrite/agents-md"><img src="https://agentmods.dev/badge/instructions/lipu-jpg/openwrite/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 | $0.00116 | $0.00116 |
| Opus 5 | $0.00058 | $0.00058 |
| Sonnet 5 | $0.00023 | $0.00023 |
| Haiku 4.5 | $0.00012 | $0.00012 |
Grade A, and why
Openwrite 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 5d 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.
What it actually says
OpenWrite workspace instructions
- Use
~/my_novelas the only project for manual, live-server, and browser QA. - Do not create or open temporary novel projects for manual QA. Extend
~/my_novelwith any fixtures needed to exercise new features. - Automated pytest cases may use isolated temporary directories, but must inject an
isolated
ProjectRegistryand must never write those paths to the user's default recent-project registry. - The OpenWrite framework repository and
reference/my_novelare not active novel projects.
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.
- 5d ago First seen · 11 lines · 116 tokens per session scan A c2699a7aca71
Openwrite AGENTS.md is an instructions file published in the GitHub repository LiPu-jpg/Openwrite (680 stars, last pushed 8d ago), licensed Apache-2.0. It adds 116 tokens to every session, about $0.0006 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
awesome-novel-agent AGENTS.md
AGENTS.md instructions for modoojunko/awesome-novel-agent, covering repository guidelines, 工作原则, 1. 编码前先思考, 2. 简洁优先 and 3. 精准修改.
writing-agent CLAUDE.md
Claude Code instructions for dongbeixiaohuo/writing-agent, covering 写稿 agent 核心路由指令（v0.10.0） and 路由顺序.
AK-Threads-booster AGENTS.md
Instructions for akseolabs-seo/AK-Threads-booster, covering ak-threads-booster — agent entry, routing, required shared reads, user data and core principles.
平台输出Skill架构规范
通用平台输出Skill与题材平台输出补丁的架构原则。定义平台平权、项目配置驱动主输出平台、平台共性规则标准化、通用-题材补丁分层设计、references文件格式与内容分工。适用于创建、审阅、维护或扩展平台输出相关Skill与补丁。.
Skill 编写规范
Use when creating, editing, reviewing, renaming, migrating, or organizing SKILL.md files, skill folders, skill references, or reusable novel-writing capabilities in this repository. Covers 通用 Skill vs 题材 Skill placement, naming prefixes, Chinese naming, frontmatter, references, and how genre skills should route to…
SKILL.md 结构模板规范
所有 SKILL.md 文件的标准结构模板。定义 CommonSkill 与 Genre Wrapper 的统一节序、缓存分层标注、references/scripts/assets 外化规范，以及结构合规检查项。适用于本项目中所有 SKILL.md 的创建、重构、审核与审计。.