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/shawnstack/quickforge/agents-mdgit clone --depth 1 https://github.com/shawnstack/quickforgeWhat 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 | $0.01057 | $0.01057 |
| Opus 5 | $0.00528 | $0.00528 |
| Sonnet 5 | $0.00211 | $0.00211 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
quickforge 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 2d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目指令
- 修改代码后,使用相关测试、构建、lint 或针对性命令进行验证。
- 默认验证命令是
npm run test、npm run lint和npm run build;小改动可优先使用针对性检查。 - 除非用户明确要求,不要创建 Git commit、tag、push 到远端或发布 npm 包。
- 当用户说“发布一个小版本” / “发一个小版本” / “小版本发布”时,遵循
docs/architecture/patch-release-runbook.zh-CN.md:提升 patch 版本,更新发布文档,运行 test/lint/build,生成 runtime/offline 包,创建 Git commit/tag/push,最后提供 npm publish 命令;默认不要直接发布 npm。
Subagent 协作
- 实现非平凡需求时,优先使用
exploresubagent 做只读仓库调研,包括定位入口、调用链、相关测试、文档/wiki 和影响面。 - 对复杂多步骤任务,可将边界清晰的子任务委托给合适的 subagent 分工推进;父 Agent 仍负责最终方案、最小化修改、结果整合和验证。
- subagent 不应绕过项目约束、审批边界或安全边界;涉及文件修改、命令执行、发布、Git 操作时仍遵循本文件现有规则。
- 简单、局部且已知文件的小改动可直接处理,无需为了形式化而调用 subagent。
项目约束
- 将
dist/、package-dist/、package-offline/视为生成产物;除非任务明确要求更新打包产物,否则不要手工修改这些目录。 - 不要新增或升级依赖,除非确有必要并说明理由;依赖变更时必须保持
package-lock.json一致。 - 优先使用 npm scripts 和跨平台命令;除非任务明确指定平台,否则不要假设只能使用 Unix shell。
- 涉及 UI、样式或交互改动时,先遵循
DESIGN_LANGUAGE.md,不要随意引入新的视觉模式。 - 如果变更影响架构、模块职责、公共入口或发布流程,应同步更新相关
docs/wiki文档;如果无需更新文档,需要说明原因。
代码 Wiki
- 项目代码 Wiki 位于
docs/wiki/README.md。 - 在理解模块、定位入口、进行较大变更或新人接手类任务时,优先读取
docs/wiki/README.md,再按需读取对应子目录文档。 - Wiki 仅作为导航和背景资料,最终判断以源码、配置和测试结果为准。
Startup Workflow
- 新会话开始先读取
docs/wiki/README.md、feature_list.json、progress.md、session-handoff.md,恢复上下文。 - 从
feature_list.json选择当前 feature(非 done 且依赖已满足的优先);本次会话只推进该 feature。 - 开始或恢复关键工作前,可用
bash init.sh执行基线验证(npm run test、npm run lint、npm run build,不安装依赖)。
Verification Commands
- 修改代码后先做针对性检查(相关测试、lint、类型检查等);小改动无需跑全套。
- 发布(release)前必须完整运行
npm run test、npm run lint、npm run build,全部通过才算完成;任何一项失败先修复,禁止在失败状态下继续发布流程。
One Feature at a Time / Stay in Scope
- 一次只处理当前 feature,不要顺带重构无关代码或修复无关问题。
- 发现与当前 feature 无关的问题,记入
progress.md的 Notes,不扩大改动范围。 - 每个改动保持最小、聚焦,改动后同步更新
feature_list.json/progress.md。
Definition of Done
- 相关测试及与改动匹配的 lint/build/针对性检查通过;发布相关改动必须完整运行
npm run test、npm run lint、npm run build。 - 文档/wiki 已按需同步;未触碰生成产物(
dist/、package-dist/、package-offline/)。 feature_list.json、progress.md、session-handoff.md已更新。
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.
- 2d ago First seen · 57 lines · 1,057 tokens per session scan A 53977b43693a
quickforge AGENTS.md is an instructions file published in the GitHub repository shawnstack/quickforge (47 stars, last pushed 2d ago), licensed MIT. It adds 1,057 tokens to every session, about $0.0053 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
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.