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/tradecatlabs/fatecat/agents-mdgit clone --depth 1 https://github.com/tradecatlabs/fatecatWrote 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/tradecatlabs/fatecat/agents-md)<a href="https://agentmods.dev/instructions/tradecatlabs/fatecat/agents-md"><img src="https://agentmods.dev/badge/instructions/tradecatlabs/fatecat/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 | $0.01639 | $0.01639 |
| Opus 5 | $0.00820 | $0.00820 |
| Sonnet 5 | $0.00328 | $0.00328 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade A, and why
fatecat 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 5d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - FateCat Enterprise Repo
目录用途
当前根目录是 FateCat 企业级系统仓库真相源:结构采用 apps、ai、domains、platform、infra、contracts、catalog、governance、shared、tools、docs、scripts、tests canonical roots;运行、测试、导出和治理入口全部从企业根解析。
项目主旨:FateCat 是面向 Agent 与应用开发者的测算基础设施,提供统一的能力协议、可复现计算核心、证据化解释层和多端交付接口。八字、紫微、黄历、梅花等体系都是独立 capability provider;复用成熟开源和稳定平台能力先于自写。
目录结构
fatecat/
├── AGENTS.md
├── compose.yaml
├── DEBUG.md
├── llms.txt
├── README.md
├── REVIEW.md
├── SKILL.md
├── apps/
├── ai/
├── domains/
│ ├── fate-analysis/
│ │ └── services/fate-core/
│ │ ├── src/
│ │ └── tests/
│ └── experience-delivery/
│ └── services/fatecat-delivery/
│ ├── src/
│ ├── scripts/
│ └── tests/
├── platform/
├── infra/
│ └── docker/
│ ├── Dockerfile.delivery
│ └── entrypoint.delivery.sh
├── contracts/
├── catalog/
├── governance/
├── shared/
├── tools/
├── docs/
│ └── deployment/
│ └── huggingface-space.md
├── tests/
├── .github/
│ ├── AGENTS.md
│ └── workflows/
│ ├── acceptance.yml
│ ├── container.yml
│ ├── hf-space-deploy.yml
│ └── quick.yml
├── references/
│ ├── commands.md
│ ├── execution-playbook.md
│ └── troubleshooting.md
└── scripts/
│ ├── acceptance.sh
│ ├── check-structure.sh
│ ├── container-build.sh
│ ├── container-release.sh
│ ├── container-smoke.sh
│ ├── check-export-hygiene.sh
│ ├── check-source-hygiene.sh
│ ├── clean-runtime.sh
│ ├── delivery-smoke.sh
│ ├── export-runtime.sh
│ ├── live-bot-smoke.sh
│ ├── production-readiness.sh
│ ├── preflight.sh
│ └── vendor-health.sh
职责边界
SKILL.md:标准 skill 入口说明。compose.yaml:本地和单机容器编排入口,只编排 delivery 容器与运行态 volume。DEBUG.md:当前调试证据、根因和回归验证记录;只承载已复现问题的诊断闭环。llms.txt:公开站点根级 AI/Agent 发现文档;集中说明 Web/API 输入、端点、证据、存储和风险边界,避免把机器契约全部堆在 Web 顶部表格。REVIEW.md:当前仓库审计结果与 release gate 结论;只记录证据、风险与交接,不承载业务源码。apps/:用户体验入口和渠道壳层。ai/:Agent、skill、Prompt、评估和 AI 监管相关入口。domains/:领域服务根;当前承载fate-core与fatecat-delivery两个生产候选服务源码、契约和测试入口。platform/:Golden Path、CI/CD、供应链和开发者平台能力。infra/:环境、容器、数据库、运行准入、安全和观测期望状态。contracts/:API、数据集、capability、profile、evidence 和策略契约。catalog/:组件发现、owner、生命周期和依赖关系。governance/:标准、流程、ADR、风险、门禁、baseline evidence、任务和迁移账本。shared/:真实复用后的薄共享库,不作为 common 垃圾桶。tools/:迁移工具、参考仓和供应链快照。docs/:人类文档入口,不替代机器契约和治理证据;docs/deployment/说明用户和维护者的云端部署路径。tests/:仓库级结构、契约、导出和跨服务测试入口。.github/:GitHub Actions 远端验收配置;只调用仓库脚本,不保存业务代码或 secret。references/:长文档、阶段门禁、输入输出契约、迁移与排障材料;其中execution-playbook.md是统一执行顺序真相源。scripts/:本地可重复执行入口;其中preflight.sh是默认预检入口,acceptance.sh是发布门禁入口,check-structure.sh是企业结构门禁,container-*.sh是容器构建、烟雾和发布入口。
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.
- 5d ago First seen · 117 lines · 1,639 tokens per session scan A 7f8ff72cc2f4
fatecat AGENTS.md is an instructions file published in the GitHub repository tradecatlabs/fatecat (203 stars, last pushed 10d ago), licensed MIT. It adds 1,639 tokens to every session, about $0.0082 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
geo-optimizer-skill AGENTS.md
AGENTS.md instructions for Auriti-Labs/geo-optimizer-skill, covering agents.md, project context, repository map, architectural rules and security rules.
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
Know-your-fate CLAUDE.md
Claude Code instructions for tf1993614/Know-your-fate, covering 命数天问 web client — claude code working guide, prompt defense baseline, project overview, repository map and architecture & request flow.
geolens CLAUDE.md
Claude Code instructions for geolens-io/geolens: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
jentic-one GEMINI.md
Gemini CLI instructions for jentic/jentic-one: Otherwise, read AGENTS.md — this repo's canonical agent guidance.
substack-gateway-oss CLAUDE.md
Claude Code instructions for jakub-k-slys/substack-gateway-oss, covering claude.md, commands, install dependencies (dev included, all workspace members), run the server (dev mode with reload) and lint.