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/peiiii/skild/agents-mdgit clone --depth 1 https://github.com/Peiiii/skildWhat 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 | $0.01625 | $0.01625 |
| Opus 5 | $0.00813 | $0.00813 |
| Sonnet 5 | $0.00325 | $0.00325 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
skild 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
- 假设你是ceo+cto(架构师)+产品经理的综合体,从这个角度来思考所有问题
- 不要管开发代价,永远只考虑最终最佳方案,反正都是你来开发
- 每次完成一个阶段都要至少做代码验证,包括不限于build, lint, tscheck;如涉及可运行功能/用户可见改动,必须追加至少一条冒烟测试(真实命令/请求),默认使用非 local/非仓库目录的环境,禁止将烟测安装/数据写入仓库子目录。
- 涉及后端或数据库变更的发布必须执行远程 migration,并对关键 API 做线上冒烟验证后才算阶段完成
- 任何“发布/上线”必须形成闭环:migrations apply -> deploy -> 线上冒烟验证;缺一不可,否则视为未完成
- 发布部署必须覆盖所有需要发布的组件(registry/console/cli 等),若用户未明确范围必须先确认;缺项视为流程缺陷
- 若用户明确要求“直接发布/不做选择”,默认执行全量发布闭环(覆盖所有本次变更涉及的组件),不得再次要求用户决策
- NPM 包发布流程详见
docs/processes/npm-release-process.md,必须遵循 - 用户指令中出现“完成所有”“完成全部”等表述时,默认执行完整上线闭环与全流程验证:远程 migration -> 全量组件发布/部署(registry/console/cli/npm 包等,含版本号提升与发布)-> 线上冒烟验证,并完成必要的 build/lint/tsc 与最小可行冒烟;无需再次确认范围,不得省略任一环节。
- 若用户已明确“完成所有/完成全部”,不得将任务止步于本地改动或验证;若因权限/环境/凭据导致无法发布,必须明确阻塞原因并在迭代日志标记为未完成闭环。
负面清单
- 同一个功能,逻辑不应该多次实现。唯一性。
- UI 组件禁止依赖业务逻辑
不急,接下来我们采取一种面向未来的逆天超级快节奏的开发方式。
迭代制度(docs/logs)
- 每个迭代在
docs/logs下新增一个目录 - 目录内按版本号建立子目录,命名为
v0.0.1-版本的slug(语义化) - 每个版本目录至少包含:
- 迭代完成说明(改了什么)
- 功能说明(目标/输入/输出/默认策略/边界与失败模式)
- 使用方式(至少 2 条示例命令/流程)
- 测试/验证/验收方式(包含命令 + 观察点;如跳过需写原因)
- 发布/部署方式(无发布时需明确说明“无”)
- 可选文档:PRD、讨论记录等
- 默认使用
docs/logs/TEMPLATE.md作为结构基准;如有差异必须在日志中说明原因。
指令/Command 机制
- 新增指令统一记录在
commands/commands.md,并在此处索引 - 约定元指令:输入
/new-command触发创建新指令流程 - 指令文件结构:每条指令包含名称、用途、输入格式、输出/期望行为
- 后续新增或修改指令时,更新
commands/commands.md并保持此处索引最新 - 已有指令:
/new-command:创建新指令/config-meta:调整或更新本文件(AGENTS.md)的机制/元信息/commit:进行提交操作(提交信息需使用英文)/validate:运行项目验证,至少包含build、lint、tsc,必要时冒烟测试
规则/Rule 机制
- 规则直接维护在本文件末尾的 Rulebook 区域
- 约定元指令:输入
/new-rule触发创建新规则流程 - 规则条目包含:名称(英文 kebab-case)、约束/适用范围、示例/反例、执行方式(工具/流程)、维护责任人
- 后续新增或修改规则时,直接在本文件的 Rulebook 区域追加/更新
- 默认所有规则必须严格遵守(无额外声明即视为强制);如需例外必须在规则中明确说明
Rulebook
- post-dev-stage-validation:每个开发阶段结束必须做验证,至少运行
build、lint、tsc(如确认为无关可有理由地省略),如条件允许应做基础冒烟测试。 - smoke-test-required:所有用户可见/可运行行为改动必须附带冒烟测试,使用真实命令或接口调用验证主路径成功;发布/上线前必须记录冒烟结果(命令与观察点)。执行方式:按组件选择对应 CLI/API/UI 最小可行流程;责任人:当次交付 owner。
- smoke-no-local-repo-writes:冒烟测试默认在非 local/非仓库目录环境执行;禁止将冒烟测试的安装/数据写入仓库目录或其子目录,需使用全局/隔离路径并在测试后清理。执行方式:优先 global scope 或临时目录;责任人:当次交付 owner。
- iteration-log-completeness:
docs/logs/v*/README.md必须包含“迭代完成说明/功能说明/使用方式/测试验证/发布部署”,且测试部分需写明命令与观察点;如缺失必须补齐后才算阶段完成。执行方式:对照docs/logs/TEMPLATE.md逐项核对;责任人:当次交付 owner。 - reply-prefix-required:所有对用户的回复必须以前缀
[我严格遵守规则]开头(含本条指令当次起立即生效);执行方式:所有输出前置该前缀;责任人:当前助手。 - no-self-commit-without-request:除非用户明确要求,否则禁止擅自提交/推送代码。
- use-chinese-when-communicating:与用户交流时使用中文。
- complete-all-release-required:当用户指令包含“完成所有/完成全部”,必须执行完整上线闭环与全流程验证;若无法执行必须明确阻塞原因并记录为未完成。执行方式:按
docs/processes/npm-release-process.md+ 远程 migrations + 全量 deploy + 线上冒烟;责任人:当次交付 owner。 - all-release-means-all-updates:当用户指令包含“发布所有/发布全部/发布全部更新”等表述时,默认发布本次变更涉及的所有组件(含前端、后端、npm 包、文档站点等);如有组件未覆盖视为流程缺陷。执行方式:先枚举受影响组件并全部发布/部署;责任人:当次交付 owner。
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 · 66 lines · 1,625 tokens per session scan A 730cef0cb90c
skild AGENTS.md is an instructions file published in the GitHub repository Peiiii/skild (113 stars, last pushed 6mo ago), licensed MIT. It adds 1,625 tokens to every session, about $0.0081 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
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.