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 skills add adsman888/agentinbox-mcp --skill agentinbox-mcpgit clone --depth 1 https://github.com/adsman888/agentinbox-mcpWrote 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/adsman888/agentinbox-mcp/agentinbox-mcp)<a href="https://agentmods.dev/skills/adsman888/agentinbox-mcp/agentinbox-mcp"><img src="https://agentmods.dev/badge/skills/adsman888/agentinbox-mcp/agentinbox-mcp/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/skills/adsman888/agentinbox-mcp/agentinbox-mcp"><img src="https://agentmods.dev/badge/skills/adsman888/agentinbox-mcp/agentinbox-mcp.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 | $0.00106 | $0.00889 |
| Opus 5.5 | $0.00042 | $0.00356 |
| Sonnet 5.5 | $0.00021 | $0.00178 |
| Haiku 4.5 | $0.00011 | $0.00089 |
Grade A, and why
agentinbox 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 2mo 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentInbox — Safe Support Inbox for AI Agents Running Stores
AgentInbox gives you (the agent) hands, memory, and a seatbelt for customer email:
- Hands: a real, persistent email inbox that receives customer mail 24/7 — even while you're offline.
- Memory: every email is parsed, thread-stripped, deduplicated, intent-classified, and stored as a structured conversation you can read any time.
- Seatbelt: you cannot send raw email. Every reply passes a guardrails engine that blocks false promises (things the business can't actually do), strips non-whitelisted URLs, and queues sends with a human-like delay so customers experience a credible human support agent.
- Revenue: an upsell engine knows what each customer owns and injects the right offer link only when contextually appropriate — and suppresses all offers during refunds, complaints, and price objections.
Setup
- Your operator signs up at https://agentinbox.dev (free tier: 1 inbox, 50 replies/month) and creates an API key from the dashboard.
- Connect via MCP (recommended, no install):
{
"mcpServers": {
"agentinbox": {
"type": "streamable-http",
"url": "https://agentinbox.dev/mcp",
"headers": { "Authorization": "Bearer aik_live_YOUR_KEY" }
}
}
}
Or via stdio: npx @agentinbox/mcp --api-key aik_live_YOUR_KEY
Or raw REST: https://agentinbox.dev/api/v1/* with Authorization: Bearer aik_live_YOUR_KEY (full reference: https://agentinbox.dev/docs/rest-api.md).
Tools
| Tool | Use for |
|---|---|
list_inboxes |
See the provisioned inbox addresses |
list_conversations |
Poll for open customer conversations (filter by status) |
get_conversation |
Read full message history + intent + customer context |
send_safe_reply |
Reply to a customer THROUGH guardrails |
escalate_to_human |
Route serious cases (anger, chargebacks, legal) to the owner |
update_knowledge |
Teach AgentInbox business facts for better replies |
Workflow
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.
- 2mo ago First seen · 62 lines · 106 tokens per session scan A 07b39a649e40
agentinbox is a skill published in the GitHub repository adsman888/agentinbox-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 106 tokens to every session and 889 once invoked, about $0.0004 per session on Opus 5.5. 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.
agentinbox compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agentinboxadsman888/agentinbox-mcp | Skill | 0 | 3mo ago | MIT | A | 106 | Claude Code, Codex |
| amazon-reviews-api-skillbrowser-act/skills | Skill | 6.3k | 3d ago | MIT | A | 124 | Claude Code, Codex |
| amazon-competitor-analyzerbrowser-act/skills | Skill | 6.3k | 3d ago | MIT | A | 48 | Claude Code, Codex |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | today | MIT | A | 60 | Claude Code |
| external-purchasesrshankras/claude-code-apple-skills | Skill | 867 | today | MIT | A | 76 | Claude Code |
| food-orderBitterbot-AI/bitterbot-desktop | Skill | 2.5k | today | MIT | A | 53 | Claude Code, Codex |
| Product Photoshoot Workflowjau123/MeiGen-AI-Design-MCP | Skill | 1.8k | yesterday | MIT | A | 111 | Claude Code |