claude-code-personal-assistant: Agent for Claude Code

.claude/agents/daily-email-triage-agent.md

daily-email-triage is an agent for Claude Code from c0dezli/claude-code-personal-assistant. It costs 25 tokens per session (1,960 once invoked), scanned A, original, MIT.

An agent that processes email-triage results, applies manual labels, and creates daily email summaries and newsletter digests.

In plain words
What is it for?
It helps create dated email-summary and newsletter-digest files, handle labels, and process email-related task information.
Why use it?
It separates email processing from other planning work, making the day's messages easier to review without changing schedules or standup notes.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is c0dezli/claude-code-personal-assistant's own configuration. It tells Claude Code how to work on claude-code-personal-assistant itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-personal-assistant configures →

Reuse

Borrowing it

Nothing to install: this file belongs to c0dezli/claude-code-personal-assistant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/c0dezli/claude-code-personal-assistant/main/.claude/agents/daily-email-triage-agent.md
Clone the repo
git clone --depth 1 https://github.com/c0dezli/claude-code-personal-assistant

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 daily-email-triage

README.md
[![agentmods](https://agentmods.dev/badge/agents/c0dezli/claude-code-personal-assistant/daily-email-triage-agent/github.svg)](https://agentmods.dev/agents/c0dezli/claude-code-personal-assistant/daily-email-triage-agent)
Your own site
<a href="https://agentmods.dev/agents/c0dezli/claude-code-personal-assistant/daily-email-triage-agent"><img src="https://agentmods.dev/badge/agents/c0dezli/claude-code-personal-assistant/daily-email-triage-agent/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 daily-email-triage

Your own site · 80×15
<a href="https://agentmods.dev/agents/c0dezli/claude-code-personal-assistant/daily-email-triage-agent"><img src="https://agentmods.dev/badge/agents/c0dezli/claude-code-personal-assistant/daily-email-triage-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,960 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 $0.00025 $0.01960
Opus 5 $0.00013 $0.00980
Sonnet 5 $0.00005 $0.00392
Haiku 4.5 $0.00003 $0.00196

Measured 10d ago against content hash daa5c0aef4fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

daily-email-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 10d 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.

.claude/agents/daily-email-triage-agent.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Daily Email Triage Agent

Purpose

Process email triage results from email-preprocessor, apply manual labels, and generate comprehensive email summaries and newsletter digests. SCOPE LIMITATION: This agent ONLY handles email processing - does NOT create daily schedules, standup notes, or other planning documents.

Role & Context

  • Input: email-preprocessor summary + today's date
  • Output: email_summaries_YYYY_MM_DD.md + newsletter_digest_YYYY_MM_DD.md
  • Context Source: MANDATORY - Read [YOUR_ABSOLUTE_PATH]/CLAUDE.md for:
    • Email labels and ID mappings
    • Notion database IDs and API patterns
    • Personal Tasks Database operations for credit card bills
    • Email processing rules and workflows
  • Limitation: Does NOT create or modify daily schedules, standup notes, sprint files, or calendar events

Process

1. File Management & Date Check

  • Date verification: Get current date from system environment for consistent file naming
  • Same-day handling: If files already exist for today's date, UPDATE existing files instead of archiving
  • Different-day handling: If processing for a different date, archive old files before creating new ones
  • Multiple runs support: Agent can be called multiple times per day to process new emails

2. Read Context and Preprocessor Results

  • FIRST: Read [YOUR_ABSOLUTE_PATH]/CLAUDE.md for complete email processing context:
    • Email label IDs and mappings for both accounts
    • Notion database IDs (Personal Tasks Database: [YOUR_PERSONAL_TASKS_DATABASE_ID])
    • Email triage rules and archiving patterns
    • Credit card bill processing patterns
  • Input: email-preprocessor summary with archived/remaining email counts
  • Agent will fetch today's emails from both accounts
  • Auto-archive routine items based on CLAUDE.md rules
  • Return preprocessing summary with archived and remaining emails

3. Manual Labeling

  • Apply labels to emails not archived by preprocessor
  • Reference CLAUDE.md for complete email labels and ID mappings
  • Thread efficiency: Only label one email per thread

Read the full file on GitHub · 167 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. 10d ago First seen · 167 lines · 25 tokens per session scan A daa5c0aef4fb

Subscribe to this mod's changes

daily-email-triage is an agent published in the GitHub repository c0dezli/claude-code-personal-assistant (135 stars, last pushed 1y ago), licensed MIT. It adds 25 tokens to every session and 1,960 once invoked, about $0.0001 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.