nanoclaw_flexagents: Skill for Claude Code

.claude/skills/add-email-archive/SKILL.md

add-email-archive is a skill for Claude Code from chiptoe-svg/nanoclaw_flexagents. It costs 57 tokens per session (1,910 once invoked), scanned A, original, MIT.

An interactive setup for sorting and processing email into an archive. It learns sender-based rules, creates a folder structure, and prepares batch processing for reaching inbox zero, meaning no emails left needing action in the inbox.

In plain words
What is it for?
Use it to configure email classification rules and folders before running the email archive process. At least one registered email account is required.
Why use it?
It turns a large inbox into a repeatable filing system based on the user's real email. It also prevents the archive process from being used before an email account is connected.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the AskUserQuestion tool.

This is chiptoe-svg/nanoclaw_flexagents's own configuration. It tells Claude Code how to work on nanoclaw_flexagents 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 nanoclaw_flexagents configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./container/build.sh.

Reuse

Borrowing it

Nothing to install: this file belongs to chiptoe-svg/nanoclaw_flexagents. 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/chiptoe-svg/nanoclaw_flexagents/main/.claude/skills/add-email-archive/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/chiptoe-svg/nanoclaw_flexagents

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 add-email-archive

README.md
[![agentmods](https://agentmods.dev/badge/skills/chiptoe-svg/nanoclaw_flexagents/add-email-archive/github.svg)](https://agentmods.dev/skills/chiptoe-svg/nanoclaw_flexagents/add-email-archive)
Your own site
<a href="https://agentmods.dev/skills/chiptoe-svg/nanoclaw_flexagents/add-email-archive"><img src="https://agentmods.dev/badge/skills/chiptoe-svg/nanoclaw_flexagents/add-email-archive/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 add-email-archive

Your own site · 80×15
<a href="https://agentmods.dev/skills/chiptoe-svg/nanoclaw_flexagents/add-email-archive"><img src="https://agentmods.dev/badge/skills/chiptoe-svg/nanoclaw_flexagents/add-email-archive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,910 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 $0.00057 $0.01910
Opus 5 $0.00028 $0.00955
Sonnet 5 $0.00011 $0.00382
Haiku 4.5 $0.00006 $0.00191

Measured 11d ago against content hash d4b5f7956e41, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

add-email-archive 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 11d 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/skills/add-email-archive/SKILL.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Email Archive

Interactive setup for the email archive system. Builds sender-based classification rules from your actual email, creates a folder taxonomy, and configures the container skill for batch processing.

Prerequisite: At least one email account must be registered. Run /add-email-account first.

Phase 1: Prerequisites

Check if already configured

MAIN_FOLDER=$(sqlite3 store/nanoclaw.db "SELECT folder FROM registered_groups WHERE is_main = 1 LIMIT 1;" 2>/dev/null)
echo "MAIN_FOLDER=${MAIN_FOLDER:-unknown}"
test -d "groups/${MAIN_FOLDER}/email-archive" && echo "CONFIGURED" || echo "NOT_CONFIGURED"

If CONFIGURED, ask the user whether to recalibrate or skip to Phase 3.

If MAIN_FOLDER is empty, ask which group folder to use.

Check email accounts

test -f "groups/${MAIN_FOLDER}/email-accounts.yaml" && cat "groups/${MAIN_FOLDER}/email-accounts.yaml" || echo "NO_ACCOUNTS"

If NO_ACCOUNTS or no enabled accounts:

No email accounts registered. Run /add-email-account first to connect your email.

Stop here.

If accounts exist, list them:

Found N registered email account(s):

  • gmail (gws) — @.com
  • outlook (ms365) — @.edu

Which accounts should be included in the archive? (default: all)

Use AskUserQuestion to confirm.

Create directory structure

mkdir -p "groups/${MAIN_FOLDER}/email-archive/calibration"
mkdir -p "groups/${MAIN_FOLDER}/email-archive/state"
touch "groups/${MAIN_FOLDER}/email-archive/overrides.jsonl"

Phase 2: Calibration

The goal is to build sender rules that cover 80%+ of email volume so the LLM only handles the long tail.

Step 2a: Initial taxonomy

Present the default categories:

Here's a starting folder taxonomy:

  • Archive/Work — work-related email
  • Archive/Personal — personal correspondence
  • Archive/Accounts — service notifications, password resets, confirmations
  • Archive/Newsletters — subscriptions, digests, mailing lists worth keeping
  • To Delete — spam, marketing, expired notifications

Want to customize? We can add subcategories later after seeing your actual email patterns.

Read the full file on GitHub · 254 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. 11d ago First seen · 254 lines · 57 tokens per session scan A d4b5f7956e41

Subscribe to this mod's changes

add-email-archive is a skill published in the GitHub repository chiptoe-svg/nanoclaw_flexagents (5 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 1,910 once invoked, about $0.0003 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.