file-collect-sort-action

file-collect-sort-action is a skill for Claude Code, Codex from ellmos-ai/skills. It costs 206 tokens per session (2,451 once invoked), scanned A, original, MIT.

A configuration-based tool for repeatedly collecting selected files from one folder and sorting them into a destination. It can recognise file types, names, or other configured patterns.

In plain words
What is it for?
It scans source folders, categorises matching files, and applies staged actions such as collecting or moving them to configured destinations.
Why use it?
It removes repetitive manual file collection and keeps recurring transfers guided by explicit rules rather than one-off instructions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It scans source folders, categorises matching files, and applies staged actions such as collecting or moving them to configured destinations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ellmos-ai/skills/file-collect-sort-action
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.

Any agent
npx skills add ellmos-ai/skills --skill file-collect-sort-action
Clone the repo
git clone --depth 1 https://github.com/ellmos-ai/skills

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 file-collect-sort-action

README.md
[![agentmods](https://agentmods.dev/badge/skills/ellmos-ai/skills/file-collect-sort-action/github.svg)](https://agentmods.dev/skills/ellmos-ai/skills/file-collect-sort-action)
Your own site
<a href="https://agentmods.dev/skills/ellmos-ai/skills/file-collect-sort-action"><img src="https://agentmods.dev/badge/skills/ellmos-ai/skills/file-collect-sort-action/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 file-collect-sort-action

Your own site · 80×15
<a href="https://agentmods.dev/skills/ellmos-ai/skills/file-collect-sort-action"><img src="https://agentmods.dev/badge/skills/ellmos-ai/skills/file-collect-sort-action.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 206 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,451 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 $0.00206 $0.02451
Opus 5 $0.00103 $0.01226
Sonnet 5 $0.00041 $0.00490
Haiku 4.5 $0.00021 $0.00245

Measured yesterday against content hash 844e8b0e6411, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

file-collect-sort-action 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/utilities/file-collect-sort-action/SKILL.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.

File Collect Sort Action

Der Nutzer hat dieses Modul bewusst passiv geparkt, bis ein konkreter Auftrag es braucht (Ticket T-20260818-916568570, User wörtlich: "ich werde irgendwann mal sagen hole aus dem ordner immer die und die dateien und sammle sie dort -> dann erkennst du den skill zu unserem modul und richtest das ein"). Dieser Skill IST die Erkennung, auf die er wartet.

Wann dieser Skill greift

Trigger sind Nutzersätze, die ein wiederkehrendes Einsammeln nach Regel beschreiben — nicht ein einmaliges "verschiebe diese eine Datei":

  • "Hole aus <Ordner> immer <Dateiart> und sammle sie in <Ziel>"
  • "Sortiere den Ordner <X> automatisch nach <Kriterium>"
  • "Sammle eingehende Dateien aus <Quelle> in <Ziel>"
  • "Räum diesen Ordner regelbasiert auf" / "verschiebe alle <Dateiart> aus <Ordner> automatisch"
  • Jede Variante, die Quelle, Erkennungsmerkmal (Dateiart/Namensmuster/Inhalt) und Ziel benennt und impliziert, dass das wiederholt passieren soll (nicht nur jetzt einmal)

Nicht dieser Skill: eine einzelne, einmalige Datei verschieben (das macht ein Agent direkt, ohne Konfigurationsschicht) — dokument-ingest (beantwortet "womit lese ich den Inhalt", nicht "wohin gehört die Datei") — inkrementelles Text-Indizieren ohne Dateien zu bewegen (gardener).

Was das Modul kann (Kurzfassung)

file-collect-sort-action (Kurzname f-csa, CLI fcsa) ist ein konfigurationsgetriebener Scan→Kategorisieren→Handeln-Agent mit drei Konfigurationsdateien und einem Verarbeitungsgedächtnis:

Datei Rolle
config.json scan_paths (Positivliste), Format-Ein-/Ausschluss, Duplikaterkennungsregeln, Sicherheitsgatter (allow_hard_delete)
categories-definitions.json Erkennungsschablonen je Kategorie (Dateiname/Endung/Inhalt), Checks/Gates, default_target, default_actions + default_stepping
action-rules.json Aktionsparameter je Kategorie (move/copy-Ziele, Duplikatmodus, Löschmodus, OCR-Backend, Platzierungsreihenfolge)
processing-csa.json wird in jeden gescannten Ordner geschrieben — bekannte Dateien, ihre Kategorie, angewandte Aktionen, wirksamer Einstellungsabdruck (Fingerprint)

Read the full file on GitHub · 167 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 Changed · +2 lines 844e8b0e6411
  2. 7d ago First seen · 165 lines · 206 tokens per session scan A 3ac2f13cdab0

Subscribe to this mod's changes

file-collect-sort-action is a skill published in the GitHub repository ellmos-ai/skills (4 stars, last pushed yesterday), licensed MIT. It adds 206 tokens to every session and 2,451 once invoked, about $0.0010 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 2026-09-03.