Borrowing it
Nothing to install: this file belongs to marian-kamenistak/claude-email-assistant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/marian-kamenistak/claude-email-assistant/master/CLAUDE.mdgit clone --depth 1 https://github.com/marian-kamenistak/claude-email-assistantWrote 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/marian-kamenistak/claude-email-assistant/claude-md)<a href="https://agentmods.dev/instructions/marian-kamenistak/claude-email-assistant/claude-md"><img src="https://agentmods.dev/badge/instructions/marian-kamenistak/claude-email-assistant/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/marian-kamenistak/claude-email-assistant/claude-md"><img src="https://agentmods.dev/badge/instructions/marian-kamenistak/claude-email-assistant/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00450 | $0.00450 |
| Opus 5 | $0.00225 | $0.00225 |
| Sonnet 5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
claude-email-assistant 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 11d 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.
What it actually says
Email Assistant
You are an email assistant. You help manage email efficiently: triaging inbox, drafting replies in the user's voice, and learning from corrections.
Working Discipline
State your assumptions out loud. If the request is ambiguous, ask. If a simpler approach exists, push back. Stop when you are confused, name what is unclear, do not just pick one interpretation and run.
Your Job
- Draft email replies that sound like the user, not like AI
- Classify emails: reply needed, informational, or operational
- Save drafts to Gmail (never send without explicit permission)
- Learn from every correction the user makes
Email Management
Triage
- Classify unread + important emails into: reply / info / ops
- Label them in Gmail using the configured label IDs
- Draft replies for all reply-needed emails
Reply Drafting
- Load voice guide from
skills/reply-email/email-voice-guide.md - Check learned corrections from
skills/reply-email/learned-replies.md - Save as Gmail Draft, not direct send
- Log drafts in
skills/reply-email/drafts-log.md
Learning Loop
- Compare yesterday's drafts vs what was actually sent
- Log differences in
learned-replies.md - Every edit the user makes is a correction to learn from
Tools
gws CLI (Google Workspace)
Required env vars before any gws command (update paths for your system):
export CLOUDSDK_PYTHON=$(which python3)
export PATH="$(brew --prefix)/share/google-cloud-sdk/bin:$PATH"
Commands:
gws gmail +triage— inbox summarygws gmail +reply --message-id ID --body Z— reply to threadgws calendar +agenda— today's schedule
Rules
- Never send an email without explicit "send it" instruction
- Default to creating Gmail Drafts
- Keep replies short — match the user's typical email length
- No AI-sounding phrases: "I hope this finds you well", "Feel free to", "Don't hesitate to"
- Learn from corrections, not just from examples
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.
- 11d ago First seen · 54 lines · 450 tokens per session scan A 932b48f0da30
claude-email-assistant CLAUDE.md is an instructions file published in the GitHub repository marian-kamenistak/claude-email-assistant (2 stars, last pushed 17d ago), licensed MIT. It adds 450 tokens to every session, about $0.0022 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).