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 rules/stringke/std-agent/rules-test-requirementsgit clone --depth 1 https://github.com/StringKe/std-agentWhat 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 | $0.00343 | $0.00343 |
| Opus 5 | $0.00171 | $0.00171 |
| Sonnet 5 | $0.00069 | $0.00069 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
rules-test-requirements 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 yesterday.
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
globs: "internal/transformer//*.go,internal/runner//.go,internal/writer/**/.go,internal/parser/**/*.go" description: 改 transformer / runner / writer / parser 必带 _test.go 防回归
测试要求
stdagent 是个"机械扩散器"，bug 修一次要管 11 个 target。任何对 transformer / runner / writer / parser 的改动都必须带测试：
- 新增 target：至少要有 plan 单测覆盖所有 type（rules / skills / commands / references / subagents）的 fanout 路径。
- 修 transformer bug：测试要能复现 bug（先红后绿），不能只在原有用例上加断言。
- 改 runner 控制流（如 prune / dry-run / strict）：单测要覆盖 flag 开/关、第一次/第二次 sync、submodule 边界等行为。
- 改 writer 落盘逻辑：测试要含 unchanged / overwrite / atomic 三类路径。
跑测试：
go test ./... # 全量
go test -race ./internal/runner/... # race detector，runner 必跑
mise run check # fmt + lint + test，提 PR 前必跑
发现已存在的 bug 但你不在改它：要么修，要么开 issue 记录，不要装作没看见。
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.
- yesterday First seen · 25 lines · 343 tokens per session scan A 207da2fabe1a
rules-test-requirements is a cursor rule published in the GitHub repository StringKe/std-agent (8 stars, last pushed 11d ago), licensed MIT. It adds 343 tokens to every session, about $0.0017 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 cursor rules, from other repositories
kotlin-ktor-development-cursorrules-prompt-file
Cursor rule "kotlin-ktor-development-cursorrules-prompt-file" from ItamarZand88/awesome-agent-conventions, covering core principles, technology stack, application structure (feature-based), application logic design and entities & data classes.
solidity-foundry-cursorrules-prompt-file
Cursor rule "solidity-foundry-cursorrules-prompt-file" from ItamarZand88/awesome-agent-conventions, covering do not compile tests when compiling via-ir and don't pollute bytecode with metadata.
java-springboot-jpa-cursorrules-prompt-file
description: "Cursor rules for Java development with Springboot and JPA integration." globs: / alwaysApply: false.
rust
Cursor rule "rust" from ItamarZand88/awesome-agent-conventions, covering rust + solana (anchor) best practices, program structure, anchor framework, serialization and testing.
swiftui-guidelines-cursorrules-prompt-file
Cursor rule "swiftui-guidelines-cursorrules-prompt-file" from ItamarZand88/awesome-agent-conventions, covering role & perspective, code generation guidelines, 1. general principles, 2. swiftui best practices (performance first) and 3. swift 6 concurrency & threading.
laravel-php-83-cursorrules-prompt-file
description: "Cursor rules for Laravel development with PHP 8.3 integration." globs: / alwaysApply: false.