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/agentteamhq/agentteam-email/agents-mdgit clone --depth 1 https://github.com/agentteamhq/agentteam-emailWrote 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/agentteamhq/agentteam-email/agents-md)<a href="https://agentmods.dev/instructions/agentteamhq/agentteam-email/agents-md"><img src="https://agentmods.dev/badge/instructions/agentteamhq/agentteam-email/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 | $0.02168 | $0.02168 |
| Opus 5 | $0.01084 | $0.01084 |
| Sonnet 5 | $0.00434 | $0.00434 |
| Haiku 4.5 | $0.00217 | $0.00217 |
Grade A, and why
agentteam-email 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.
How it starts
The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Requirements
Documentation
Agents must keep AGENTS.md limited to durable workflows and read or update the
owning documentation before changing documented behavior.
Agents must not edit any AGENTS.md file without explicit current-task approval
for that specific file.
README.md is the public product and project presentation surface; agents must
not use it for architecture requirements, security rules, runtime contracts,
release procedures, validation workflows, or operational runbooks.
Before work involving authentication, authorization, Better Auth, credentials, encryption, sessions, cookies, API keys, tokens, JWT, OAuth, JWKS, secret storage, security-sensitive routes, or anything that could be security related, agents must stop, read SECURITY.md, and follow it.
Architecture And Integration Boundaries
Before changing existing product concepts, architecture boundaries, route surfaces, authentication terms, integration terms, account/domain ownership, or settings semantics, agents must read ARCHITECTURE.md and preserve the vocabulary and ownership model defined there.
When ARCHITECTURE.md points to a package or directory
AGENTS.md as the owning rule surface, agents must read that file before
changing behavior in that scope.
Before proposing or changing any code, configuration, documentation, task, Compose file, chart, test, or runtime wiring that connects one service to another, agents must read ARCHITECTURE.md and the owning service architecture documentation.
This applies to service-to-service integration, network or listener binding, hostnames, ports, Compose or Kubernetes routing, RPC clients, SMTP relay paths, OAuth callbacks, webhooks, provider boundaries, and any other connection between services. Connection-specific changes include adding, removing, or changing URLs, base URLs, listen addresses, network aliases, target services, protocols, ports, client factories, callback paths, relay paths, health checks, credential boundaries, or provider endpoints. Agents must identify the documented contract, the current runtime evidence, and the specific mismatch before editing. Agents must not infer connectivity changes from a local symptom, temporary dev topology, or current broken code alone. If observed behavior matches the documented contract, agents must not change wiring and must continue validation at the next failing boundary.
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 · 262 lines · 2,168 tokens per session scan A d591da9d4b0a
agentteam-email AGENTS.md is an instructions file published in the GitHub repository agentteamhq/agentteam-email (60 stars, last pushed 1mo ago), licensed MIT. It adds 2,168 tokens to every session, about $0.0108 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
microfeed AGENTS.md
AGENTS.md instructions for microfeed/microfeed, covering repository guidance, development workflow, instance management and cloudflare deployment, source architecture and theme repositories.
microfeed CLAUDE.md
Claude Code instructions for microfeed/microfeed, a project described as: an agentic cms self-hosted on cloudflare, for podcasts, blogs, photos, videos, documents, and curated urls.
mailroom AGENTS.md
Instructions for iannuttall/mailroom, covering agent notes, public package contract, repository map, documentation and onboarding rules and architecture rules.
mailroom CLAUDE.md
Instructions for iannuttall/mailroom, a project described as: Private email infrastructure for people and AI agents.
agents AGENTS.md
AGENTS.md instructions for cloudflare/agents, covering agents.md, project overview, repository structure, nested agents.md files and setup.
cloudflare-workers-nextjs-saas-template AGENTS.md
AGENTS.md instructions for LubomirGeorgiev/cloudflare-workers-nextjs-saas-template, covering project context, vinext, general coding rules, control flow and comments.