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/re0wiki/wiki-bot/agents-mdgit clone --depth 1 https://github.com/re0wiki/wiki-botWrote 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/re0wiki/wiki-bot/agents-md)<a href="https://agentmods.dev/instructions/re0wiki/wiki-bot/agents-md"><img src="https://agentmods.dev/badge/instructions/re0wiki/wiki-bot/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 | $0.10194 | $0.10194 |
| Opus 5 | $0.05097 | $0.05097 |
| Sonnet 5 | $0.02039 | $0.02039 |
| Haiku 4.5 | $0.01019 | $0.01019 |
Grade A, and why
wiki-bot 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — wiki-bot
Re:Zero Fandom Wiki(https://rezero.fandom.com/zh)的维护机器人,基于 Pywikibot。 主要工作:把英文站内容同步到中文站,并对中文站做译名/格式规范化。
知识归处(仓库文档 vs Hermes skill)
- 与本仓库/wiki 绑定的知识只写进本仓库文档(AGENTS.md 放精简规则与指针,
docs/放详细配方),随 git 提交——这是唯一权威来源。不要存为 Hermes skill:skill 在仓库之外、不随代码走,曾经因此漂移出相互矛盾的副本。任务结束时的「save as skill」惯例对本仓库知识不适用,改为写进docs/。 - 判断标准是「知识从哪里来、在哪里验证」,不是「理论上能不能用在别处」:源自本仓库实践的 pywikibot / Fandom / Cloudflare 限流 / 模板审计等知识,即使看似通用,也算本仓库知识,进
docs/。(有过教训:曾被重新框架成「通用 Fandom 知识」存成 skill。) - 分工:把知识写进
docs/是主 agent(有文件工具)的职责,任务收尾时主动做。回合结束后的后台 skill review(只有 memory/skill 工具的 fork agent)对本仓库知识应直接放弃('Nothing to save')——它碰不了仓库文件,不要建/改 skill,也不要把知识代为塞进 memory。 - skill 只用于跨仓库/跨资源的流程(例如译名核验横跨 OCR 语料库与 gh issue)。新建 skill 前检查内容不与
docs/重复。 - 文档记录原则:规则、原因、不变量进文档;仓库自身的变更事件(何时改了什么、谁改的)归 git log,不写编年史——文档里出现「2026-xx-xx 改了某文件」类句子即腐化信号。两类例外保留日期:对外部系统的实测观测(Fandom/Cloudflare 行为,日期=时效元数据)、wiki 侧决策与状态(wiki 没有决策日志,这里是唯一记录处)。
环境
- Python 3.14(
.python-version,pyproject.toml要求>=3.14),uv 管理,有uv.lock。 - 安装:
uv sync(default-groups = "all")。pywikibot 的全部可选依赖以 extras 形式声明在 dev 组(pywikibot[html,http,...]),覆盖其 requirements.txt,随 submodule 更新自动跟随。 - 运行脚本:
uv run python <script>(仓库根目录)。uv 按 cwd 的 pyproject.toml 定位项目.venv,天然绕过 PATH 上 Hermes 自身 venv 的裸python(3.11、无项目依赖),且每次运行顺带校验环境与 uv.lock 同步(开销可忽略,--no-sync可跳过)。 - pywikibot 是 git submodule(fork:
github.com/re0wiki/pywikibot,upstream 是 wikimedia/pywikibot)。克隆要--recurse-submodules(否则uv sync会因路径缺失失败)。更新 submodule 后提交信息写chore: update pywikibot。 - pywikibot 通过
[tool.uv.sources]以 editable 方式从 submodule 路径装入 venv({ path = "pwb", editable = true }),submodule gitlink 是唯一版本锁,无需再同步 uv.lock 里的 commit。pyproject.toml里的[tool.ty.environment] extra-paths = ["./pwb"]是必须的:ty 无法静态解析 PEP 660 editable finder,删掉会导致全项目 unresolved-import。 - Lint:
ruff check/ruff format(PATH 里没有 ruff 时用uv run ruff ...,ty 同理;pyproject.toml里 extend-exclude 了 pwb 子模块、logs/ 与 *.md(保留手工对齐的代码块注释),不要给它们 lint;scripts/oneoff/归档脚本纳入正常检查,归档前需先过 lint/format/ty)。类型检查用ty(src.exclude排除 pwb 与 logs/,正常应为 0 诊断)。 - 离线单测:
pytest tests/(不触 wiki;覆盖译名表一致性、watchdog 纯函数;PYWIKIBOT_DIR由 tests/conftest.py 设置)。临时探索脚本写成 .py 放logs/(scratch,gitignored)、从仓库根目录跑(uv run python logs/_foo.py);docs 只写结论不引用其路径。从子目录跑则 pywikibot 找不到user-config.py(cwd 不参与配置发现时按用户目录找)。Wiki 侧改动验证方式仍是-s/--simulate干跑 + 上 wiki 查编辑结果。 - Secrets:
user-password.py(BotPasswords,gitignored,勿读勿提交)。
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.
- 3d ago First seen · 125 lines · 10,194 tokens per session scan A 17bd4f51234e
wiki-bot AGENTS.md is an instructions file published in the GitHub repository re0wiki/wiki-bot (5 stars, last pushed 4d ago), licensed MIT. It adds 10,194 tokens to every session, about $0.0510 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.