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/choyiny/saasmail/claude-mdgit clone --depth 1 https://github.com/choyiny/saasmailWrote 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/choyiny/saasmail/claude-md)<a href="https://agentmods.dev/instructions/choyiny/saasmail/claude-md"><img src="https://agentmods.dev/badge/instructions/choyiny/saasmail/claude-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 | $0.00337 | $0.00337 |
| Opus 5 | $0.00169 | $0.00169 |
| Sonnet 5 | $0.00067 | $0.00067 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
saasmail CLAUDE.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 today.
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
saasmail
Self-hosted email server on Cloudflare Workers. README.md is the overview; full documentation lives in docs/ (setup, configuration, architecture, and one page per feature).
Contributor and coding-agent conventions (CI gates, Prettier, PR semver labels, drizzle migrations including data-only --custom): see AGENTS.md.
Development
- Use
yarnfor all dependency commands (not npm) - Backend: Hono + Zod OpenAPI routes in
worker/src/routers/ - Frontend: React + Tailwind in
src/ - Database: Drizzle ORM with D1 in
worker/src/db/ - Run
yarn tsc --noEmitto type-check before committing - Run
yarn testfor tests - Run
yarn format/yarn format:checkbefore pushing (CI enforces Prettier)
Skills
/saasmail-onboarding— Interactive setup wizard for deploying a new saasmail instance/use-saasmail— How to call a deployed saasmail instance's HTTP API to send emails (raw or via templates) and enroll recipients in sequences/create-saasmail-template— Authoring email templates: the{{variable}}grammar, conditional and repeating{{#section}}rules, escaping, and the required-vs-optional send contract/update-saasmail— Rebase a fork ontoupstream/main(links the upstream remote if needed)
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.
- today Changed · +27 tokens per session f91106b10b03
- 5d ago First seen · 23 lines · 310 tokens per session scan A 1bce8c1c6ac2
saasmail CLAUDE.md is an instructions file published in the GitHub repository choyiny/saasmail (247 stars, last pushed yesterday), licensed Apache-2.0. It adds 337 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 2026-08-30.
Other instructions, from other repositories
baerly-storage CLAUDE.md
Toolchain, verification matrix, module map, conventions, anti-patterns. The main agent entry point.
moltworker AGENTS.md
Instructions for cloudflare/moltworker, covering agent instructions, project overview, project structure, key patterns and environment variables.
cloudbox AGENTS.md
Instructions for acoyfellow/cloudbox, covering cloudbox agent guide, canonical commands, deploy model, cloudflare account boundaries and required production secrets.
hqbase AGENTS.md
AGENTS.md instructions for HQBase/hqbase, covering hqbase workspace guide, boundaries and quality gate.
cld-flare-maxxing AGENTS.md
AGENTS.md instructions for AbhiiGatty/cld-flare-maxxing, covering cld-flare-maxxing — operating contract, what this is, golden rules, vocabulary: what "deploy it" (and similar) actually means and confirming a deploy landed.
kolea CLAUDE.md
Claude Code instructions for robconery/kolea, covering 🐦 kōlea, 📚 docs — read before you write, 🔁 phase commands, 🛠 stack and 🧭 layering.