agentmods.dev

triage-inbox

triage-inbox is a skill for Claude Code from chrisblattman/claudeblattman. It costs 19 tokens per session (7,396 once invoked), scanned A, original, MIT.

An email-organising workflow that classifies Gmail messages and applies configured labels and filters. It uses message headers and content to find emails that native Gmail filters may miss.

In plain words
What is it for?
Use it to scan an inbox, identify messages such as announcements or expenses, and place them under configured labels.
Why use it?
It reduces the manual work of sorting messages into folders and finding emails that were not labelled correctly.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths.

not rated 476repo +4 today A scan 19 tokens original MIT

Good fit Use it to scan an inbox, identify messages such as announcements or expenses, and place them under configured labels.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chrisblattman/claudeblattman/triage-inbox
View source ↗ chrisblattman/claudeblattman claudeblattman.com
Install

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.

Any agent
npx skills add chrisblattman/claudeblattman --skill triage-inbox
Clone the repo
git clone --depth 1 https://github.com/chrisblattman/claudeblattman

Made for: Claude Code.

Wrote 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.

agentmods badge for triage-inbox

README.md
[![agentmods](https://agentmods.dev/badge/skills/chrisblattman/claudeblattman/triage-inbox/github.svg)](https://agentmods.dev/skills/chrisblattman/claudeblattman/triage-inbox)
Your own site
<a href="https://agentmods.dev/skills/chrisblattman/claudeblattman/triage-inbox"><img src="https://agentmods.dev/badge/skills/chrisblattman/claudeblattman/triage-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.

agentmods 80×15 button for triage-inbox

Your own site · 80×15
<a href="https://agentmods.dev/skills/chrisblattman/claudeblattman/triage-inbox"><img src="https://agentmods.dev/badge/skills/chrisblattman/claudeblattman/triage-inbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,396 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.07396
Opus 5.5 $0.00008 $0.02958
Sonnet 5.5 $0.00004 $0.01479
Haiku 4.5 $0.00002 $0.00740

Measured today against content hash 544291e2cb5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

triage-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.

skills/triage-inbox/SKILL.md · 617 lines

How it starts

The opening of the file, as written. The whole thing — 617 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Smart Inbox Triage

v1.5 — Added Phase 5.5: student reply detection with batch-confirm

Scan your inbox for emails that should be in labeled folders (@ToRead, @Announcements, @School, Expenses-Pending, Auto-Archive, etc.) but are not filtered there yet. Uses header and content heuristics that Gmail's native filters cannot replicate.

Prerequisites

  • Gmail MCP — google_workspace_mcp with Gmail tools enabled
  • Email policy config — ~/.claude-assistant/config/email-policy.md (VIP list, auto-archive rules, filter lists). Download the template from the GitHub repo (see First-Time Setup).
  • Triage config — ~/.claude-assistant/config/triage-config.md (label IDs, expense vendors, scoring thresholds, classification overrides). Download the template from the GitHub repo (see First-Time Setup).
  • Gmail label IDs — You need the internal Gmail label IDs for each target label. Run mcp__google_workspace__list_gmail_labels to find them, then put them in triage-config.md.

First-Time Setup

  1. Create config directory:

    mkdir -p ~/.claude-assistant/config ~/.claude-assistant/state ~/.claude-assistant/logs

  2. Create triage-config.md from the template. At minimum, fill in:

    • Label IDs — run mcp__google_workspace__list_gmail_labels with your email to find IDs for your target labels (@ToRead, @Announcements, @School, Expenses-Pending, Expenses-Personal, Expenses-Uncertain, Auto-Archive, @Family, @FYI)
    • Expense Vendor Domains — domains like amazon.com, uber.com, etc. that send receipts
    • Classification Overrides — senders you always want routed a specific way

  3. Create email-policy.md from the template. At minimum, fill in:

    • VIP lists (Tier 1: family, journals, compliance; Tier 2: collaborators, team members)
    • @Family addresses — personal contacts who should never be auto-triaged
    • Auto-Archive rules — senders or patterns to always archive

Read the full file on GitHub · 617 lines

Changes

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.

  1. today First seen · 617 lines · 19 tokens per session scan A 544291e2cb5e

Subscribe to this mod's changes

triage-inbox is a skill published in the GitHub repository chrisblattman/claudeblattman (476 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 7,396 once invoked, about $0.0001 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 2026-11-06.

Productivityacademic-researchai-toolsclaude-aimkdocs
Related

triage-inbox compared with skills from other repositories

triage-inbox next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
triage-inboxchrisblattman/claudeblattmanSkill476todayMITA19Claude Code
skill-extractflonat/flonat-researchSkill1493d agoMITA43Claude Code
update-focusflonat/flonat-researchSkill1493d agoMITA29Claude Code
session-healthflonat/flonat-researchSkill1493d agoMITA58Claude Code
low-code-platformstravisjneuman/.claudeSkill107yesterdayMITA54Claude Code, Codex
agent-desktoptravisjneuman/.claudeSkill107yesterdayMITA38Claude Code, Codex
reorgflonat/flonat-researchSkill1493d agoMITA53Claude Code, Codex