Borrowing it
Nothing to install: this file belongs to a1024053774/design-integrity-guardrails. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/a1024053774/design-integrity-guardrails/main/AGENTS.mdgit clone --depth 1 https://github.com/a1024053774/design-integrity-guardrailsWrote 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/a1024053774/design-integrity-guardrails/agents-md)<a href="https://agentmods.dev/instructions/a1024053774/design-integrity-guardrails/agents-md"><img src="https://agentmods.dev/badge/instructions/a1024053774/design-integrity-guardrails/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/a1024053774/design-integrity-guardrails/agents-md"><img src="https://agentmods.dev/badge/instructions/a1024053774/design-integrity-guardrails/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01553 | $0.01553 |
| Opus 5 | $0.00776 | $0.00776 |
| Sonnet 5 | $0.00311 | $0.00311 |
| Haiku 4.5 | $0.00155 | $0.00155 |
Grade A, and why
design-integrity-guardrails 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent 工作约定
目的
完成当前任务的最小充分改动。规划可以深入,执行必须克制;没有证据证明必要性, 不要发货。用户要求、仓库约定和更高优先级规则始终优先。
开工前与上下文
- 第一次实质编辑前,按任务规模和风险读取足够的实现、直接调用方、相关配置、 测试和用户约束;小而局部且契约明确的改动不要求扫描无关调用链,跨模块、外部 边界、行为或架构不确定的改动才扩展读取范围。文档、格式或机械改动通常只需读 目标文件和格式约定。不要先改代码再猜意图。
- 开始前给出最小计划:目标、非目标、验收条件、仍未知的事实。小改动可压缩成一句话, 但不能省略验收条件。
- 只有歧义会改变结果、范围、风险或授权时才提问;否则明确假设并继续。用户修正 某项决策标准后,将它应用到相关范围,不只修正被点名的例子。
- 只使用当前任务需要的 Skill。普通执行不默认拉起多个 Agent。
- 若需求、领域规则、外部行为或验收条件存在可能改变方向的缺口,先使用
reality-first-engineering。把事实标为observed、measured、inferred或unknown,为关键未知绑定最小可证伪实验;未解除时返回BLOCKED/INCOMPLETE, 不得用猜测、mock-only 分支或 fallback 伪装成完成。同一架构决策批次只过一次门。
同一计划内的后续编辑沿用已经建立的上下文;只有范围、关键前提、直接调用方、验收 证据发生变化,或上下文已不足以作出决定时才重读。
改动边界
- 在根因所在职责层修改,并同步必要调用方;不要为了少碰正确抽象而增加旁路 API、 适配器层、兼容分支、默认值、重试或 feature flag。
- 新增第二条生产路径时,必须能指出真实调用方/契约、故障模式、所有权、优先级和 移除条件;否则停下来改小方案。
- 用户请求在明确范围内授权正常的连续执行:读取、编辑、运行相关测试、查看 diff、 生成计划和其他可逆本地检查不需要逐项重新确认。只有不可逆或外部副作用、实质 扩大范围/授权,或会改变方向的关键未知才停下确认。
- 发现前提错误、范围正在膨胀,或正确修复超出授权时,停止实现,报告根因、影响和 最小选项。停下来上报是合规的成功结局,不是失败。
- 看到自己开始堆抽象、为罕见情况加保护、触碰无关文件、复制旧逻辑或用测试掩盖扩 范围时,立即重写成更小的计划。
- 安全、隐私、凭据、数据丢失、权限、迁移和外部副作用按真实威胁模型处理;评审、 审计和解释默认只读,计划本身不构成提交、发布或部署授权。
测试、验收与复审
- 测试只服务当前改动的验收。先运行相关现有测试;绿色测试不自动证明需要新增抽象。
- 只有现有覆盖无法证明新增行为,或用户明确要求时才加测试。每个新增测试都要说明 它验证哪条验收条件、没有它会漏掉哪个真实回归,以及为什么现有证据不足。测试 数量和代码长度不是充分性的标准;“一个主路径+一个失败路径”只是开始检查的启发, 不是配额或上限。需要更多覆盖时按不同契约、边界或故障模式说明理由;没有证据时 不要新增矩阵、快照、端到端框架或测试基础设施。
- 测试应从真实入口观察行为,输入和 oracle 尽量独立于生产实现;不要用测试数量、 复杂度或绿色结果为新增抽象辩护。
- 修 bug、改测试或验证修复时使用
evidence-first-testing:先保留红态或可复现反例, 再做最小修复,最后跑相关回归;无法建立反事实时如实说明测试证据有限。 - 新增 catch/except、fallback、兼容路径、并行 API 或特殊分支且 scanner 命中时,
候选版本冻结后只做一次
design-integrity-review;发现问题集中修复,最多一次定向 复审。同一回答的迭代不逐次启动 reviewer。 - 涉及
eval、benchmark、autoresearch、harness、golden、oracle或测试 是否独立验证时,由design-integrity-review路由到behavioral-acceptance-review和一个acceptance-auditor。实现者新增的测试只是待审证据,不是唯一 oracle。
唯一账本与文档
- 长期项目使用
project-to-act作为唯一持久事实源;Reality、进度、版本和验收都写 回已有 canonical ledger,不创建REALITY.md、第二套计划或并行状态文件。未配置的 一次性项目不因 Skill 加载自动初始化。 - 人只需要一个当前摘要;详细记录只为可追溯证据服务,带来源、状态和最后验证时间。 不要为了显得完整新增重复或容易过时的 Markdown;派生文档不得凌驾于代码、实测事实 或 canonical ledger。
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 Changed · +12 lines · +283 tokens per session 42e084947f4a
- 8d ago First seen · 68 lines · 1,270 tokens per session scan A 219e1f605b66
design-integrity-guardrails AGENTS.md is an instructions file published in the GitHub repository a1024053774/design-integrity-guardrails (0 stars, last pushed 4d ago), licensed MIT. It adds 1,553 tokens to every session, about $0.0078 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.