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/flame211186/founder-decision-agent/agents-mdgit clone --depth 1 https://github.com/flame211186/founder-decision-agentWrote 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/flame211186/founder-decision-agent/agents-md)<a href="https://agentmods.dev/instructions/flame211186/founder-decision-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/flame211186/founder-decision-agent/agents-md.svg" alt="Measured on agentmods" 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 | $0.01145 | $0.01145 |
| Opus 5 | $0.00573 | $0.00573 |
| Sonnet 5 | $0.00229 | $0.00229 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
founder-decision-agent 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 4d 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.
What it actually says
Agent Development Operating Rules
本文件约束所有参与本仓库开发的编码 Agent。它的作用是防止长周期开发中的目标漂移、上下文压缩、未经验证的“完成”以及为了堆代码而堆代码。
1. 每次工作前必须恢复项目状态
开始任何实质工作前,按顺序读取:
PROJECT_STATE.yamldocs/PROJECT_CHARTER.mddocs/REQUIREMENTS_TRACEABILITY.mddocs/DECISIONS.mddocs/ROADMAP.mddocs/WORKLOG.md
如果当前任务涉及评估输出,继续读取 docs/PRODUCT_SPEC.md 和 docs/EVALUATION_METHODOLOGY.md;如果涉及代码结构或技术选型,继续读取 docs/ARCHITECTURE_PLAN.md。
处理评测失败、报告质量或安全问题时,还必须读取 docs/FAILURE_TAXONOMY.md。
聊天内容可以补充这些文件,但不得用模糊的聊天记忆覆盖已经确认的项目决定。新要求与现有文档冲突时,先显式指出冲突并记录决定。
2. 质量优先规则
- 不以文件数量、代码行数、功能数量或“看起来完整”作为完成标准。
- 不在阶段质量门未通过时提前实现后续阶段。
- 优先完成最能降低核心产品风险的实验、规格和评测。
- 单 Agent 能可靠完成的工作,不为了展示复杂度而改成多 Agent。
- 不因某个框架流行而锁定框架;技术选择必须对应已确认需求。
- 不把模型自评、测试存在、命令退出码为零或文档声称成功,单独当作质量证明。
3. 需求与决策管理
- 每项实现必须能映射到
REQ-*需求编号。 - 任何改变产品边界、公开承诺、数据处理方式、评估结论或核心架构的决定,都要写入
docs/DECISIONS.md。 - 未决定事项必须保持“待决定”,不得在实现中暗中替用户作出不可逆选择。
- 可逆、低风险的实现细节可以先采用明确记录的默认值。
- 完成一项需求后,必须在需求追踪表中加入可检查的验证证据。
4. 事实、推断与反幻觉
- 评估结果必须区分:用户提供、外部事实、模型推断、情景假设、未知。
- 外部可变事实必须记录来源、发布日期或访问日期。
- 数值计算使用确定性代码,不允许模型在无依据时生成精确数字。
- 不能验证的信息要降级为假设或未知,不能用流畅措辞伪装成事实。
- 搜索结果、模型摘要和二手文章不是天然可靠来源;优先原始资料、监管机构、公司官方材料和可复核数据。
- “另一轮模型批评”不能替代引用验证、结构校验和人工评审。
5. 安全与用户利益
- 产品提供创业想法与融资准备分析,不提供证券买卖建议,不保证融资或商业成功。
- 涉及法律、税务、证券发行、医疗、重大财务决策时,必须标注适用地区和专业人士复核需要。
- 默认不代表用户联系投资人、发布内容、签署文件、提交申请、转账或执行其他外部写操作。
- 用户身份资料和想法记录按敏感数据处理;默认最小收集、最小传输、可导出、可删除。
- 日志、测试固件和错误报告不得包含密钥或未经同意的真实私密想法。
6. 代码与验证
- 核心业务必须与 UI、模型提供商、搜索提供商和存储实现解耦。
- 所有公共输入输出使用版本化 Schema。
- 每个工具必须有参数校验、超时、错误类型、权限边界和测试。
- 新增或改变评估行为时,必须同步更新评测案例。
- 单元测试不依赖真实付费 API;真实模型评测与普通 CI 分离。
- 对外结论必须经过结构验证、引用验证和关键数值验证。
7. 工作区边界
- 默认只修改
/Users/frame/Documents/lmao agent。 /Users/frame/Documents/lmao app是潜在集成项目,目前包含用户自己的未提交修改。除非用户明确授权具体集成任务,否则只允许只读检查,不得修改、格式化、提交或清理。- 不覆盖或删除不属于当前任务的用户文件。
8. 每次工作结束
结束前必须:
- 更新
docs/WORKLOG.md; - 更新受影响的需求状态、决策和路线图;
- 运行与改动范围相称的验证;
- 清楚说明已经证明的内容、尚未证明的内容和下一决策点;
- 只有全部显式需求都有直接证据时,才可以声称项目完成。
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.
- 4d ago First seen · 80 lines · 1,145 tokens per session scan A e92ec5452362
founder-decision-agent AGENTS.md is an instructions file published in the GitHub repository flame211186/founder-decision-agent (0 stars, last pushed 16d ago), licensed Apache-2.0. It adds 1,145 tokens to every session, about $0.0057 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
open-swe AGENTS.md
AGENTS.md instructions for langchain-ai/open-swe, covering agents.md, project, commands, architecture and entrypoints.
LangBot AGENTS.md
AGENTS.md instructions for langbot-app/LangBot, covering agents.md, quick facts, essential commands, where to look and cross-repo sdk work.
open-swe CLAUDE.md
Claude Code instructions for langchain-ai/open-swe, a project described as: An Open-Source Asynchronous Coding Agent.
awesome-ChatGPT-repositories CLAUDE.md
Claude Code instructions for taishi-i/awesome-ChatGPT-repositories, covering awesome-chatgpt-repositories — claude code guide, repository structure, plugin skill (when installed via /plugin), local standalone command (when repo is cloned) and compact data format (plugins/awesome-chatgpt-search/data/).
dify AGENTS.md
AGENTS.md instructions for langgenius/dify, covering agents.md, repository gotchas and frontend workflow.
dify CLAUDE.md
Claude Code instructions for langgenius/dify, a project described as: Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.