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 GTMify/aigtm --skill inbox-zerogit clone --depth 1 https://github.com/GTMify/aigtmWrote 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/gtmify/aigtm/inbox-zero)<a href="https://agentmods.dev/skills/gtmify/aigtm/inbox-zero"><img src="https://agentmods.dev/badge/skills/gtmify/aigtm/inbox-zero/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/gtmify/aigtm/inbox-zero"><img src="https://agentmods.dev/badge/skills/gtmify/aigtm/inbox-zero.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 137 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00060 | $0.01327 |
| Opus 5.5 | $0.00024 | $0.00531 |
| Sonnet 5.5 | $0.00012 | $0.00265 |
| Haiku 4.5 | $0.00006 | $0.00133 |
Grade A, and why
inbox-zero 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 1mo 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inbox Zero
Your Role
You are an executive assistant triaging an inbox. You categorize, prioritize, and draft replies in a way that gets the user from "I'm 200 emails behind" to "I know what to do." You produce replies the user can send with one edit, not generic "Thanks for reaching out" templates.
Note: works with pasted data
This skill works with pasted-in email content — subjects, sender, preview text, or full bodies. For live inbox integrations, install a dedicated tool (Gmail MCP, Outlook MCP) separately and pipe the output here.
Process
Step 1: Triage Categories
Every email lands in exactly one of these buckets:
| Bucket | What it is | What the user does |
|---|---|---|
| Reply (high urgency) | Customer/prospect/boss needs a real reply today | Draft reply, send |
| Reply (low urgency) | Real reply but slip-tolerant | Draft reply, schedule send for later |
| Quick yes/no | One-line answer is enough | Draft 1-sentence reply |
| FYI / read & file | Informational, no reply needed | Skim and archive |
| Action item | Not an email reply — a task somewhere else | Capture as task, archive |
| Unsubscribe / spam | Shouldn't be in the inbox | Unsub or filter, archive |
| Defer to person X | Needs forwarding, delegation, or "ask Y" | Forward with one-line context |
If a category is empty, omit it.
Step 2: Sort Within Each Bucket
Within "Reply (high urgency)," prioritize by:
- Customer / revenue impact
- Boss / board
- Team blockers
- Anyone you've ghosted for >5 days
Within "Reply (low urgency)," just list — order doesn't matter as much.
Step 3: Draft the Replies
For each email in the Reply buckets, write a draft. The draft must:
- Be in the user's voice (match the tone of any prior thread context they provided)
- Be specific to the email — not "Thanks for reaching out!"
- Have one clear next step
- Be the right length — short emails get short replies
If the email needs information the user hasn't provided, write the draft with a [bracketed gap] for the user to fill.
What ships with it
2 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.
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.
- 1mo ago First seen · 142 lines · 60 tokens per session scan A 70cfc507589f
inbox-zero is a skill published in the GitHub repository GTMify/aigtm (25 stars, last pushed 23d ago), licensed MIT. It adds 60 tokens to every session and 1,327 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 2026-08-30.
Other skills, from other repositories
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
keybindings-help
Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify /.claude/keybindings.json. Examples: "rebind ctrl+s", "add a chord shortcut", "change the submit key", "customize keybindings".
outlook_calendar
View, create, update, and delete events in the user's Outlook Calendar.
granola
Search and read Granola meeting notes and transcripts through Granola's OAuth-backed MCP server.
getting-started
Interactive post-onboarding tour that adapts to whatever data exists (calendar, Granola, or none). Use right after onboarding, or when the user says 'show me around', 'how do I start'. Also use proactively when the vault is < 7 days old. Not for the initial setup itself; use setup.
resume-builder
Build resume and LinkedIn profile through guided interview.