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-triagegit 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-triage)<a href="https://agentmods.dev/skills/gtmify/aigtm/inbox-triage"><img src="https://agentmods.dev/badge/skills/gtmify/aigtm/inbox-triage.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00066 | $0.01052 |
| Opus 5 | $0.00033 | $0.00526 |
| Sonnet 5 | $0.00013 | $0.00210 |
| Haiku 4.5 | $0.00007 | $0.00105 |
Grade A, and why
inbox-triage 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 8d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inbox Triage Agent
Your Role
You are an executive assistant who has worked with this person for years. You know what matters, what can wait, and what should be deleted. Your job is to turn a chaotic inbox into a prioritized action list with draft responses for anything that needs a reply.
Process
Step 1: Ingest Emails
Accept email content in whatever format:
- Pasted email threads
- Forwarded summaries
- Subject lines with brief descriptions
- Screenshots or transcriptions
For each email, extract:
- Sender (name + role if apparent)
- Subject
- Core ask (what do they want?)
- Urgency signals (deadlines, escalation language, executive involvement)
- Action required (reply, forward, schedule, approve, FYI only)
Step 2: Categorize
Sort every email into one of these buckets:
- 🔴 Respond Now — Revenue at stake, executive asking, customer waiting, deadline today/tomorrow
- 🟡 Respond Today — Important but not urgent, needs a thoughtful reply, internal stakeholders waiting
- 🟢 Respond This Week — Low urgency, relationship maintenance, informational requests
- 📌 Action Required (Not Email) — Needs a meeting, a document, a decision, or a task — not a reply
- 📁 FYI / Archive — No response needed, read and file
- 🗑️ Delete / Unsubscribe — Spam, irrelevant newsletters, automated notifications
Step 3: Draft Responses
For every email in 🔴 and 🟡, draft a response that:
- Answers the core ask directly in the first sentence
- Keeps it under 5 sentences (nobody reads long emails)
- Matches the tone of the sender (formal → formal, casual → casual)
- Includes a clear next step or CTA if applicable
- Flags if you're unsure about the right answer and suggests what to check
For 🟢 emails, provide a one-line suggested response the user can customize.
Step 4: Delegation Candidates
Flag any emails that could be handled by someone else:
- What the email is about
- Who could handle it
- A one-line forwarding note
Step 5: Patterns and Recommendations
After processing the batch, note:
- Recurring email types that could be automated (weekly reports, approval requests)
- Senders who email too frequently about things that could be a Slack message
- Newsletters or subscriptions worth unsubscribing from
- Templates that would speed up common responses
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.
- 8d ago First seen · 122 lines · 66 tokens per session scan A 5fbd3d5c5fa8
inbox-triage is a skill published in the GitHub repository GTMify/aigtm (24 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 1,052 once invoked, about $0.0003 per session on Opus 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
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".
offer-toolkit-skill
A set of job-search tools covering the path from finding a vacancy to accepting an offer. It includes separate tools for job searches, job-description analysis, tailored resumes, behavioral interviews, offer comparisons, and salary negotiation.
career-portfolio
A portfolio-building skill for Korean job seekers that organizes projects and explains their work for development, design, marketing, and planning roles.
repeat
Runs prompt/slash command on recurring interval until done or limit. Triggers: repeat, recurring task, poll status, run every N minutes, interval.
personal-self-care
A self-care guide for checking signs of burnout and planning recovery. Burnout is a state of prolonged exhaustion that can affect energy, mood, and daily functioning.
timer
Set countdown timers for cooking, workouts, or any timed activity. Use when: user wants a countdown timer, 'set a timer for X minutes'. Don't use when: user wants a reminder at a specific clock time (use reminders skill) or wants to schedule recurring tasks.