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 terrylica/cc-skills --skill mailbox-consolidationgit clone --depth 1 https://github.com/terrylica/cc-skillsWrote 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/terrylica/cc-skills/mailbox-consolidation)<a href="https://agentmods.dev/skills/terrylica/cc-skills/mailbox-consolidation"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/mailbox-consolidation/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/terrylica/cc-skills/mailbox-consolidation"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/mailbox-consolidation.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 | $0.00153 | $0.02636 |
| Opus 5.5 | $0.00061 | $0.01054 |
| Sonnet 5.5 | $0.00031 | $0.00527 |
| Haiku 4.5 | $0.00015 | $0.00264 |
Grade A, and why
mailbox-consolidation 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 12d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mailbox consolidation into one Workspace hub
Self-Evolving Skill: This skill improves through use. If a step is wrong, Google changed behaviour, or a workaround was needed, fix this file immediately. Only record real, reproducible findings, and never add a real address, domain, tenant, rule ID or customer detail: this plugin is public.
The setup: one hub mailbox in a Google Workspace tenant (a shared front-desk inbox) receives everything that used to go to several sources. Each source keeps its own copy. Staff reply from the hub using "send mail as" for each source, so correspondents see no change.
Each source type gets a different mechanism, and each mechanism fails silently in its own way. The rules below were all measured, not taken from documentation.
1. Survey first: read the live state, never the plan
Before changing anything, read each mailbox's actual settings through the Gmail API. Reading needs only gmail.settings.basic or gmail.readonly, and it can be done for consumer accounts too.
GET users/me/settings/autoForwarding → {"enabled": false} means nothing is forwarded, whatever the docs say
GET users/me/settings/forwardingAddresses → is the hub even listed, and is it "accepted" or "pending"?
GET users/me/settings/filters → filters that archive, delete or forward
Then prove where the hub's mail actually came from, using metadata only (no bodies). The Delivered-To chain tells the three routes apart:
| Route | Delivered-To on the hub's copy |
To: header |
|---|---|---|
| History import (Data migration) | hub and source | source |
| Consumer-Gmail auto-forwarding | hub and source | source |
| Admin routing rule "Also deliver to" | hub only | source |
Imported and forwarded copies look alike, so use dates. If the newest source-addressed message in the hub is older than mail the source received since, forwarding is off and only the import ever ran.
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.
- 12d ago First seen · 109 lines · 153 tokens per session scan A 0ec916f04820
mailbox-consolidation is a skill published in the GitHub repository terrylica/cc-skills (0 stars, last pushed today), licensed MIT. It adds 153 tokens to every session and 2,636 once invoked, about $0.0006 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 2026-10-08.
Other skills, from other repositories
low-code-platforms
Low-code and internal tool platforms including Retool, Supabase, Appsmith, Tooljet, n8n, and Zapier. Use when building admin panels, internal tools, workflow automations, or integrating low-code platforms with custom code.
nav-compact
Clear conversation context while preserving knowledge via context marker. Use when user says "clear context", "start fresh", "done with this task", or when approaching token limits.
host-ssh
Run PowerShell on Windows hosts or a POSIX shell on macOS/Linux hosts over SSH, via the machine registry in the guide Environment (GASSHMACHINES). Use when the user needs host OS tasks — drives, dotnet, Playwright, processes, SSH into their laptop or desktop — not file I/O on paths already visible in the workspace…
social-media-strategy
Platform-specific tactics, content optimization, audience growth, and analytics-driven social media strategy. Use when planning a social strategy, optimizing posts for a specific platform, or growing and measuring an audience.
book-publishing
Multi-book content, voice, and production workflows for nonfiction authoring. Use when planning a book, maintaining consistent voice across chapters, structuring a manuscript, or running an end-to-end publishing pipeline.
frankx-daily-execution
Executes Frank's daily workflow using the FrankX agent system, Starlight Intelligence, and productivity methods. Use when planning Frank's day, running a focused work sprint, or turning intentions into a concrete execution plan.