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 agentmods add skills/boazbk/codex_assistant/email-attention-flownpx skills add boazbk/codex_assistant --skill email-attention-flowgit clone --depth 1 https://github.com/boazbk/codex_assistantWrote 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/boazbk/codex_assistant/email-attention-flow)<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>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 | $0.00079 | $0.01928 |
| Opus 5 | $0.00039 | $0.00964 |
| Sonnet 5 | $0.00016 | $0.00386 |
| Haiku 4.5 | $0.00008 | $0.00193 |
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.
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.mdfirst. - Read
log.mdbefore surfacing or replying to anything. - Read
email_templates.mdwhen 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
- 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.
- Run a second pass that excludes obvious bulk categories such as promotions, forums, social, and updates to build a human-origin shortlist.
- 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.
- 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.
- Use
search_email_idsor equivalent coverage checks to verify the result set is not suspiciously sparse. - Read bodies for shortlisted messages whose snippets are insufficient, and read full threads when the latest responder or next actor is ambiguous.
- Check all relevant addresses visible in the Gmail results, prior handled threads, and message headers. Do not assume one address is enough.
- 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.
- Remove anything already logged in
log.mdas handled or marked off. - Surface encrypted or otherwise unreadable personal emails as unresolved items rather than ignoring them.
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.
- 6d ago First seen · 132 lines · 79 tokens per session scan A 731268da59c3
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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.