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/rashidazarang/email-intel/agents-mdgit clone --depth 1 https://github.com/rashidazarang/email-intelWrote 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/rashidazarang/email-intel/agents-md)<a href="https://agentmods.dev/instructions/rashidazarang/email-intel/agents-md"><img src="https://agentmods.dev/badge/instructions/rashidazarang/email-intel/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 5.1 | $0.00616 | $0.00616 |
| Opus 5 | $0.00308 | $0.00308 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
email-intel 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on email-intel
Rules for any agent or human who edits this repository. CLAUDE.md is a symlink to this file, so every tool reads the same guidance.
The bar
Every change passes the full gate before commit.
swift build -Xswiftc -warnings-as-errors
swift test
vale README.md SECURITY.md CONTRIBUTING.md SUPPORT.md AGENTS.md
./scripts/check-versions.sh
Code rules
No force unwraps and no as! in Sources/**. Handle the nil case or fail with a message.
No new dependencies. The package has zero external dependencies. Keep it that way. DNS runs through URLSession, SMTP through Network.framework, JSON through Foundation.
Strict concurrency everywhere. All models stay Sendable. Stateful resolvers and probers stay actors.
Fix every instance. When you find a bug pattern, search for it across the tree and fix all of it.
A fix must simplify. If your fix adds a layer, a flag, or a special case, look for the version that removes one instead.
Writing rules
All prose follows a reduced ASD-STE100 style. Prose means README, docs, commit messages, PR text, and CHANGELOG entries.
- Never use an em dash. Use a period, a comma, a colon, or parentheses.
- Write short sentences. Target 20 words for an instruction, 25 for a description.
- Give one instruction per sentence. Use a numbered list for a sequence.
- Use the active voice and the present tense. Name the actor.
- Keep the articles. Write "run the script", not "run script".
- Use one name for one thing. The product is email-intel. The library is
EmailIntel. The CLI isemail-intel-cli. The server isEmailIntelMCP. - No marketing words. Describe what the tool does.
Tables, code blocks, JSON examples, and CHANGELOG history are exempt.
Version rules
EmailIntel.version in Sources/EmailIntel/EmailIntel.swift is the only version constant. The CLI and the MCP server read it. When shipped behavior changes:
- Bump
EmailIntel.versionand the version innpm/package.json. - Add a CHANGELOG entry with the same version and today's date.
- Tag the release as
v<version>after merge and push the tag. - The Release workflow builds, tests, publishes to npm with provenance, and attaches the tarball to the GitHub release. Do not publish by hand.
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 · 56 lines · 616 tokens per session scan A 1fbeb9235aa1
email-intel AGENTS.md is an instructions file published in the GitHub repository rashidazarang/email-intel (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 616 tokens to every session, about $0.0031 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
dns-mcp CLAUDE.md
Claude Code instructions for mclose/dns-mcp, covering dns mcp server — developer guide, auth: cimd, not a dcr shim (changed 2026-08-26), layout, build & test and adding a tool.
email-templates CLAUDE.md
Instructions for ColorlibHQ/email-templates, covering claude.md, repository purpose, layout, commands and editing or adding a template.
better-email-mcp CLAUDE.md
Claude Code instructions for n24q02m/better-email-mcp, covering claude.md - better-email-mcp, commands, setup, lint & type check and fix.
cli AGENTS.md
Instructions for nylas/cli, covering ai coding agent guidelines, quick reference: shared helpers, quick reference: adding a new feature and quick reference: credential storage.
postmark-mcp CLAUDE.md
Claude Code instructions for ActiveCampaign/postmark-mcp, covering claude.md, project overview, commands, architecture and mcp tools registered.
olkcli CLAUDE.md
Instructions for rlrghb/olkcli, covering claude.md, what is this project?, quick reference, architecture and key patterns.