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 skills/carbeneai/forge/emailmanagernpx skills add CarbeneAI/Forge --skill emailmanagergit clone --depth 1 https://github.com/CarbeneAI/ForgeWrote 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/skills/carbeneai/forge/emailmanager)<a href="https://agentmods.dev/skills/carbeneai/forge/emailmanager"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/emailmanager.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 | $0.00053 | $0.02676 |
| Opus 5 | $0.00026 | $0.01338 |
| Sonnet 5 | $0.00011 | $0.00535 |
| Haiku 4.5 | $0.00005 | $0.00268 |
Grade B, and why
EmailManager scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo cp ~/.claude/skills/EmailManager/linux-service/emailmanager.service /etc/systemd/system/ How it starts
The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EmailManager
Intelligent email management system for PAI that monitors Gmail accounts (personal + workspace), filters spam/phishing with 4-layer detection, and surfaces legitimate emails via Telegram notifications.
Agent: Philemon
Biblical character who received Paul's most important personal letter — a masterclass in diplomatic communication and message handling. Perfect for an email management agent.
Architecture
Gmail API (Personal) ─┐
├→ EmailMonitor.ts → SpamFilter.ts → Telegram Notification
Gmail API (Workspace) ─┘
- Auth: OAuth2 with encrypted refresh tokens
- Polling: Every 2 minutes via systemd service on your host machine
- Storage: JSON files in
data/(gitignored) - Notifications: Telegram (reuses existing PAI bot)
Quick Start
1. Setup OAuth (one-time per account)
# Personal Gmail
bun ~/.claude/skills/EmailManager/tools/OAuth2Setup.ts --account personal
# Workspace Gmail
bun ~/.claude/skills/EmailManager/tools/OAuth2Setup.ts --account workspace
2. Test Gmail Access
# List unread emails
bun ~/.claude/skills/EmailManager/tools/GmailClient.ts list --account personal --query "is:unread" --max 5
3. Test Spam Filter
# Analyze a specific message
bun ~/.claude/skills/EmailManager/tools/SpamFilter.ts analyze --account personal --message-id <id>
4. Run Monitor (manual)
# Dry run - no notifications
bun ~/.claude/skills/EmailManager/tools/EmailMonitor.ts --once --dry-run
# Single run with notifications
bun ~/.claude/skills/EmailManager/tools/EmailMonitor.ts --once
# Daemon mode
bun ~/.claude/skills/EmailManager/tools/EmailMonitor.ts --daemon
5. Service Management (Linux host)
~/.claude/skills/EmailManager/tools/manage.sh start
~/.claude/skills/EmailManager/tools/manage.sh status
~/.claude/skills/EmailManager/tools/manage.sh stop
Priority Gate System (Phase 4)
For high-volume inboxes (300+ emails/day), the Priority Gate drastically reduces Telegram noise by scoring emails on "decision required" probability.
What ships with it
22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .gitignore 388 B
- bun.lock 20 KB
- data/.gitignore 71 B
- linux-service/emailmanager.service 863 B
- package.json 289 B
- reference/SpamDetectionGuide.md 5.0 KB
- tools/CalendarClient.ts 22 KB runs code
- tools/DailyDigest.ts 16 KB runs code
- tools/EmailCategorizer.ts 15 KB runs code
- tools/EmailConfig.ts 14 KB runs code
- tools/EmailMonitor.ts 28 KB runs code
- tools/GmailClient.ts 14 KB runs code
- tools/manage.sh 2.8 KB runs code
- tools/MeetingScheduler.ts 17 KB runs code
- tools/OAuth2Setup.ts 11 KB runs code
- tools/PriorityGate.ts 15 KB runs code
- tools/ResponseDrafter.ts 15 KB runs code
- tools/SpamFilter.ts 15 KB runs code
- tsconfig.json 713 B
- workflows/Monitor.md 3.8 KB
- workflows/Respond.md 2.7 KB
- workflows/Schedule.md 4.2 KB
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 · 317 lines · 53 tokens per session scan B c784d4f886d0
EmailManager is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 2,676 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
aod-orchestrate
Multi-feature orchestration skill that bridges /aod.blueprint output to parallel wave execution. Groups synced GitHub Issues by ICE priority tier (P0/P1/P2) into sequential waves, creates Task records, spawns batch sessions via the orchestrator API, monitors completion, and reports results. Supports --issues…
code-execution-helper
Guide for using code execution capabilities to perform parallel batch processing, conditional filtering, and data aggregation. This skill should be used when agents need to analyze multiple files efficiently, validate large result sets, aggregate data from multiple sources, or reduce token consumption through…
root-cause-analyzer
Implements 5 Whys root cause analysis methodology for systematic debugging and problem resolution. Use this skill when you need to find root cause, run 5 whys analysis, analyze recurring problems, or perform systematic debugging. Guides developers through structured analysis, documents findings in institutional…
panguard
AI agent security platform — audit skills, scan for threats, and run 24/7 protection with 9,700+ detection rules.
detecting-aws-credential-exposure-with-trufflehog
Detecting exposed AWS credentials in source code repositories, CI/CD pipelines, and configuration files using TruffleHog, git-secrets, and AWS-native detection mechanisms to prevent credential theft and unauthorized account access.
tachi-control-analysis
Domain knowledge for compensating controls analysis — control category definitions with detection patterns, evidence criteria with effectiveness classification, and residual risk calculation with recommendation generation. Loaded on-demand by the control-analyzer agent during codebase scanning and risk assessment…