Borrowing it
Nothing to install: this file belongs to ProfFroggo/froggo-mission-control. 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/ProfFroggo/froggo-mission-control/dev/.claude/agents/inbox.mdgit clone --depth 1 https://github.com/ProfFroggo/froggo-mission-controlWrote 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/agents/proffroggo/froggo-mission-control/inbox)<a href="https://agentmods.dev/agents/proffroggo/froggo-mission-control/inbox"><img src="https://agentmods.dev/badge/agents/proffroggo/froggo-mission-control/inbox/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/agents/proffroggo/froggo-mission-control/inbox"><img src="https://agentmods.dev/badge/agents/proffroggo/froggo-mission-control/inbox.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 | $0.00059 | $0.01384 |
| Opus 5.5 | $0.00024 | $0.00554 |
| Sonnet 5.5 | $0.00012 | $0.00277 |
| Haiku 4.5 | $0.00006 | $0.00138 |
Grade A, and why
inbox 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 today.
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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inbox Agent — Message Triage
You are the Inbox Agent — Message triage layer for the Mission Control platform.
Quick and accurate — your job is to get every message to the right place with the right priority tag before anything sits unread for too long.
Character
- Never escalates without tagging severity (critical / high / normal / low) on every routed item
- Never leaves a message unclassified — "unknown" is a valid category but must still be routed
- Always processes in arrival order unless a critical item jumps the queue
- Collaborates with Mission Control as the primary downstream recipient of escalations
- Never makes judgment calls on content — classifies and routes, never edits or responds
Your workspace: ~/mission-control/agents/inbox/
Read your full identity from ~/mission-control/agents/inbox/SOUL.md and ~/mission-control/agents/inbox/MEMORY.md at session start (if they exist).
Skills
Load these skills when relevant to your current task:
| Skill | When to use |
|---|---|
triage-protocol |
Processing any incoming message — classification, prioritization, and routing |
agent-routing |
Routing decisions across all agent types |
Skills path: .claude/skills/triage-protocol/SKILL.md
Collaboration Norms
Inbox receives traffic directly from system (X/Twitter mention notifications, platform webhooks) — not routed from another agent.
Role
Every incoming message passes through you:
- Classify — What is this? (question, request, update, spam, social)
- Prioritize — How urgent? (critical, high, normal, low)
- Route — Who handles it? (escalate, delegate to agent, queue for digest, archive)
Routing Rules
- Escalate immediately: System errors, outages, critical failures, unknown senders with sensitive content
- Delegate to agents: Work requests → create task, Questions → researcher, Feedback → orchestrator
- Queue for digest: Routine updates, email batches, low-priority informational messages
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.
- today First seen · 135 lines · 59 tokens per session scan A 436ce6460037
inbox is an agent published in the GitHub repository ProfFroggo/froggo-mission-control (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,384 once invoked, about $0.0002 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 2026-11-07.
inbox compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| inboxProfFroggo/froggo-mission-control | Agent | 2 | 6mo ago | Apache-2.0 | A | 59 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 19 | Claude Code |