saasmail AGENTS.md

Repository instructions for saasmail, a self-hosted email server running on Cloudflare Workers.

In plain words
What is it for?
Use them when contributing to saasmail, reading its product or contributor documentation, running checks, handling database changes, or preparing a pull request.
Why use it?
They map the important documentation and spell out the package, formatting, type-checking, unit-test, and end-to-end test requirements.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/choyiny/saasmail/agents-md
Clone the repo
git clone --depth 1 https://github.com/choyiny/saasmail

Made for: Codex, OpenCode.

Per session 1,548 This file is loaded in full into every session.
When invoked 1,548 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01548 $0.01548
Opus 5 $0.00774 $0.00774
Sonnet 5 $0.00310 $0.00310
Haiku 4.5 $0.00155 $0.00155

Measured 3d ago against content hash bd13a5349d3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

saasmail 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 3d 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.

AGENTS.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent / contributor notes

Conventions for coding agents (and humans) working in this repo. Product docs live in README.md; licensing and human contribution flow in CONTRIBUTING.md; Claude Code skills in CLAUDE.md.

Doc map

Doc Use for
README.md Setup, deploy, local dev, API overview
CONTRIBUTING.md Fork/PR process, Apache 2.0, CoC
migrations/README.md drizzle-kit generate / apply details
.github/pull_request_template.md PR checklist maintainers expect (not a CI enforcer)

Tooling

  • Use yarn, not npm (yarn install --frozen-lockfile in CI).
  • Format: yarn format before push. Husky runs lint-staged → Prettier on staged *.{js,jsx,ts,tsx,json,css,md,html} at commit; CI runs full-tree yarn format:check (so husky alone is not enough if you skip staging a dirty file).
  • Typecheck: yarn tsc --noEmit
  • Unit tests: yarn test (invokes vitest run --config vitest.config.test.ts — bare vitest run hits the wrong pool config and fails to start).
  • E2E: yarn test:e2e (Playwright; wipes local D1 — re-seed with yarn db:seed:dev afterward). Needs DEMO_MODE=1 + DISABLE_PASSKEY_GATE=true in .dev.vars, and http://localhost:8788 in TRUSTED_ORIGINS in wrangler.jsonc (see .dev.vars.example / wrangler.jsonc.example and README “End-to-end tests”).

Local yarn test prerequisites

Vitest uses @cloudflare/vitest-pool-workers, which requires a present wrangler.jsonc (gitignored) and dist/client/. Match CI:

Read the full file on GitHub · 83 lines

Changes

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.

  1. 3d ago First seen · 83 lines · 1,548 tokens per session scan A bd13a5349d3f

Subscribe to this mod's changes

saasmail AGENTS.md is an instructions file published in the GitHub repository choyiny/saasmail (246 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,548 tokens to every session, about $0.0077 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.