Borrowing it
Nothing to install: this file belongs to Olorinm/agent-friendly-services. 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/Olorinm/agent-friendly-services/main/AGENTS.mdgit clone --depth 1 https://github.com/Olorinm/agent-friendly-servicesWrote 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/olorinm/agent-friendly-services/agents-md)<a href="https://agentmods.dev/instructions/olorinm/agent-friendly-services/agents-md"><img src="https://agentmods.dev/badge/instructions/olorinm/agent-friendly-services/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/olorinm/agent-friendly-services/agents-md"><img src="https://agentmods.dev/badge/instructions/olorinm/agent-friendly-services/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 | $0.04726 | $0.04726 |
| Opus 5.5 | $0.01890 | $0.01890 |
| Sonnet 5.5 | $0.00945 | $0.00945 |
| Haiku 4.5 | $0.00473 | $0.00473 |
Grade A, and why
agent-friendly-services 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 13d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目核心理念
本项目帮助普通个人找到适合 Agent 调用、用于完成真实用户任务的外部服务。我们尽可能全面地发现候选,研究真实、常见的需求,再通过公平实测比较服务的可靠性、接入门槛和使用开销,帮助用户及其 Agent 选择更有性价比的服务。
判断项目有没有进展,要看是否发现了更多有依据的候选、是否更理解真实用户需求、是否增加了帮助用户选服务的可靠结论。跑通测试、增加测试数量或统一格式只是手段;不能用它们代替上述目标。
旅行是探索这套机制的第一个样本。我们希望形成能适用于更多分类、持续修正和维护的方法,而不是把旅行的具体做法固定成所有分类的模板。
每一步为什么存在
项目由四个角色推进,服务于同一个目标:帮用户找到适合 Agent 使用的高性价比服务。
| 步骤 | Agent做什么 | 要留下的结果 |
|---|---|---|
| 发现服务 | 按大类/子类广泛查找,遵守收录约束 | 候选表:服务商、入口、个人接入条件和来源 |
| 确定任务 | 调研真实需求,参考成熟benchmark的任务设计 | 任务表:任务、预计输入、预计输出、完成与未完成标准 |
| 执行测试 | 按生成的委托,在总控提供的独立环境中实际调用服务 | 用户结果、交付物及实际阻碍;运行器采集用量与日志 |
| 独立验收 | 按冻结要求核对真实结果与证据 | 完成结论、依据、接入门槛与费用来源,交总控录入结果表 |
总控负责调度、准备资源、监控、复核与汇报;发现服务、任务设计、执行测试、独立验收分别交给对应角色。执行与验收必须分属独立新会话,不能让被测 Agent 给自己判分;历史由主持会话兼任验收的记录保留原有说明。研究过程可以自由展开,不要求把中间步骤都变成文档;重点是填好候选表、任务表和结果表。
被测Agent只获得任务prompt、原始工作材料、指定服务入口和本轮统一规定的工具/凭据/资源,以及单独冻结的通用执行角色指令。不能继承本次讨论、研究档案、其他服务的结果、参考答案或为它提前写好的调用脚本,也不加载本仓库的整体工作指令。固定Agent、模型与预算;需要查文档、安装或编写调用代码,由它在该次运行内完成并计入开销。研究用的AGENTS.md约束准备工作,不能被自动塞进被测会话。
完成由事先写好的验收标准判断。所有任务使用同一套三项检查,不为每类问题另找标准答案:有据,交付中的每个结论都能在运行器采集的该次真实服务响应或独立读回中核对。可追溯到本次调用、参数和来源且未截断的实际字段输出,也可以支持已完整呈现的字段;不机械要求整份 HTTP 正文或响应头。已经证明与实际响应矛盾的内容是错误;因采集遗漏、截断或来源缺口无法判断的内容是证据不足,不能直接称为编造或服务失败;合规,交付满足委托中写明的全部要求,如日期、范围、条件、格式,以及“最便宜”“全部”这类相对服务返回结果的要求;互证,同期同题其他服务的结果作为交叉参考,答案一致提高可信度,出现分歧时标记并进入抽查,但分歧本身不判失败,也不以多数答案为准。前两项决定是否完成;互证只发现疑点。几家服务共享同一错误上游时互证无法发现,因此按比例抽样,用官方数据或人工复核结果。碰巧有现成官方数据的题,可在冻结前取得参考作为额外核对,但这是可选的加强,不是出题的前提。Agent实际输入、其中缓存输入与输出token分别留底,总用量为输入加输出。模型费用由脚本提取本地session的逐次请求用量、与运行器整轮汇总核对后,依据保存的LiteLLM价格表逐次计价再求和;原始session只留本地,公开记录只含用量与来源hash。保留价格版本、日期与未知原因,不视为账户实付。服务费用优先依据回执、用量或账单;缺金额时可按已查证的用量与单价估算,注明来源。确认免费记0,缺依据记未知。用量和服务费用缺失就记未知,缓存输入不重复相加。首先测能否完成基础用户任务,再增加场景深度;“找机票”不自动增加最便宜、购买、付款核验或复杂家庭限制。调用成功本身不是任务完成,环境故障也不能算服务失败。
测试输入尽量保持真实用户的表达和必要资料。用户要求、运行环境与验收办法分别维护;不要把日志格式、进程安排、证据索引等测试工作伪装成用户需求交给被测 Agent。证据采集与验收优先由运行器和外部复核完成;尚需 Agent 配合的部分要明确披露,其开销不能直接解释为日常用户的使用开销。详细指导可能帮助完成任务,也可能增加负担;相同指导不自动等于公平。任务或指导方式改变后另记版本,保留历史前提。
生成任务时,先写简短、目标优先的用户委托;原始材料与运行环境分别提供。必要交付要求融进委托,不把任务表的“预计输出、完成标准、未完成标准”逐列拼成 prompt。验收要求必须能追溯到委托或工作材料;隐藏的是测试实现和标准答案,不能隐藏用户要求。按用户结果验收,允许 Agent 自行选择字段和操作顺序。
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.
- 13d ago Changed · +78 tokens per session 5fe3a8c04b12
- 15d ago Changed · +479 tokens per session fdce9376cc75
- 1mo ago Changed · +190 tokens per session 7a05527e499a
- 1mo ago Changed · +1 lines · +49 tokens per session c791b8fc85e4
- 1mo ago Changed · +234 tokens per session d76b510dc486
- 1mo ago Changed · +23 lines · +1,076 tokens per session f85c55336c9d
- 1mo ago Changed · +8 lines · +932 tokens per session 0ad458c7ed62
- 1mo ago Changed · +23 lines · +781 tokens per session 632ff614a1c9
- 1mo ago First seen · 48 lines · 907 tokens per session scan A eab6fa286dd1
agent-friendly-services AGENTS.md is an instructions file published in the GitHub repository Olorinm/agent-friendly-services (2 stars, last pushed 2d ago), licensed MIT. It adds 4,726 tokens to every session, about $0.0189 per session on Opus 5.5. 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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.