auto-tag

An email-classification and labeling tool for Gmail. It sorts messages into five categories and proposes Gmail labels for them, with user confirmation before applying changes.

In plain words
What is it for?
It is for reviewing selected messages, suggesting labels based on their content, and applying approved labels.
Why use it?
It reduces inbox clutter while keeping the user in control of automatic labeling.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/axisrow/claude_code_gmail_plugin/auto-tag
Any agent
npx skills add axisrow/claude_code_gmail_plugin --skill auto-tag
Clone the repo
git clone --depth 1 https://github.com/axisrow/claude_code_gmail_plugin

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 530 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00041 $0.00530
Opus 5 $0.00020 $0.00265
Sonnet 5 $0.00008 $0.00106
Haiku 4.5 $0.00004 $0.00053

Measured yesterday against content hash 168f88f57baf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto-tag 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 yesterday.

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/auto-tag/SKILL.md · 63 lines

What it actually says

Auto-Tag Gmail Emails

Analyze emails and apply label recommendations with user confirmation.

Arguments

$ARGUMENTS — optional Gmail search query. If empty, use recent INBOX messages.

Step 1: Fetch emails and labels

  1. Use Gmail MCP gmail_search_messages to fetch emails (use query from $ARGUMENTS or in:inbox, limit 10-20)
  2. Use Gmail MCP gmail_list_labels to get available user labels
  3. For each email, use gmail_read_message to get full content and current labels

Step 2: Classify with tagging context

For each email, classify into one of 5 categories:

  • 🟢 PERSONAL / ЛИЧНОЕ — addressed personally, requires response
  • 🔵 USEFUL NEWSLETTER / ПОЛЕЗНАЯ РАССЫЛКА — consciously subscribed content
  • 🟡 IMPORTANT NOTIFICATION / ВАЖНОЕ УВЕДОМЛЕНИЕ — transactional, worth reading
  • 🟠 NOISE / ШУМ — repetitive alerts, noise
  • 🔴 SPAM / МУСОР — marketing, promotions, spam

For each email provide:

  1. Category (with emoji)
  2. Brief summary
  3. Recommendation
  4. Suggested labels from the available user label list

Step 3: Generate tagging proposal

Create a summary table of proposed changes:

  • For each email: abbreviated subject, current labels, proposed new labels (by name)
  • Only propose labels that are NOT already on the email

Step 4: Confirm with user

Ask the user to confirm: "Apply these tags? (y/n)"

Do NOT proceed without explicit user confirmation.

Step 5: Apply tags (only after confirmation)

After user confirms, construct JSON and pipe to the apply script:

echo '{"actions": [{"message_id": "MSG_ID", "add": ["Label_ID"]}]}' | python3 ~/.claude/scripts/gmail-analyzer/modify_labels.py

Report results: how many emails were tagged successfully.

If user declines, report "Cancelled." and do not apply.

Respond in the user's language.

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. yesterday First seen · 63 lines · 41 tokens per session scan A 168f88f57baf

Subscribe to this mod's changes

auto-tag is a skill published in the GitHub repository axisrow/claude_code_gmail_plugin (3 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 530 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens