email-attention-flow

email-attention-flow is a skill for Claude Code, Codex from boazbk/codex_assistant. It costs 79 tokens per session (1,928 once invoked), scanned A, original, MIT.

An inbox-review workflow for finding emails that you personally need to answer within a chosen time period. It checks all relevant Gmail addresses and separates likely personal requests from bulk mail.

In plain words
What is it for?
Use it to audit Gmail for unanswered personal conversations, group messages by reply confidence, and suggest replies based on saved templates and past notes.
Why use it?
It reduces the risk of missing a reply you owe while avoiding time spent on promotions, mailing lists, and other low-priority messages.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

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/boazbk/codex_assistant/email-attention-flow
Any agent
npx skills add boazbk/codex_assistant --skill email-attention-flow
Clone the repo
git clone --depth 1 https://github.com/boazbk/codex_assistant

Made for: Claude Code, Codex.

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 email-attention-flow

README.md
[![agentmods](https://agentmods.dev/badge/skills/boazbk/codex_assistant/email-attention-flow.svg)](https://agentmods.dev/skills/boazbk/codex_assistant/email-attention-flow)
Your own site
<a href="https://agentmods.dev/skills/boazbk/codex_assistant/email-attention-flow"><img src="https://agentmods.dev/badge/skills/boazbk/codex_assistant/email-attention-flow.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,928 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 5.1 $0.00079 $0.01928
Opus 5 $0.00039 $0.00964
Sonnet 5 $0.00016 $0.00386
Haiku 4.5 $0.00008 $0.00193

Measured 6d ago against content hash 731268da59c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

email-attention-flow 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 6d 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.

skills/email-attention-flow/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Email Attention Flow

Use this skill for inbox-attention scans, reply-needed audits, and email-response workflows in this repo.

Required Local Files

  • Read AGENTS.md first.
  • Read log.md before surfacing or replying to anything.
  • Read email_templates.md when the scan may include standard request types.

Core Goal

Maximize recall for personal threads where the user is plausibly the next actor, especially emails they personally owe a reply to. Prefer a few false positives over a false negative on personal-response coverage, while still filtering obvious bulk and list noise. If there is meaningful doubt whether the user still owes a response, include the item in a lower-confidence bucket instead of silently dropping it.

Scan Workflow

  1. Start with a broad all-mail search for the full requested timeframe. Do not assume the inbox alone contains every thread the user still owes a response to.
  2. Run a second pass that excludes obvious bulk categories such as promotions, forums, social, and updates to build a human-origin shortlist.
  3. Run an additional pass tuned for personal reply-needed mail. Favor searches and filters that catch direct human conversation, recent back-and-forth, and mail addressed to one of the user's known or visible addresses.
  4. If the timeframe is more than a few days, do not rely only on the first page of results. Paginate or search by time slices so older actionable mail is not missed.
  5. Use search_email_ids or equivalent coverage checks to verify the result set is not suspiciously sparse.
  6. Read bodies for shortlisted messages whose snippets are insufficient, and read full threads when the latest responder or next actor is ambiguous.
  7. Check all relevant addresses visible in the Gmail results, prior handled threads, and message headers. Do not assume one address is enough.
  8. For each shortlisted personal thread, explicitly classify whether the user owes a reply, owes some other action, is waiting on the other side, or the thread is unclear.
  9. Remove anything already logged in log.md as handled or marked off.
  10. Surface encrypted or otherwise unreadable personal emails as unresolved items rather than ignoring them.

Read the full file on GitHub · 132 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. 6d ago First seen · 132 lines · 79 tokens per session scan A 731268da59c3

Subscribe to this mod's changes

email-attention-flow is a skill published in the GitHub repository boazbk/codex_assistant (5 stars, last pushed 4mo ago), licensed MIT. It adds 79 tokens to every session and 1,928 once invoked, about $0.0004 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.