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 skills add khalilbenaz/claude-skills-collection --skill file-processor-subagentgit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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/khalilbenaz/claude-skills-collection/file-processor-subagent)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/file-processor-subagent"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/file-processor-subagent/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.
<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/file-processor-subagent"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/file-processor-subagent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00080 | $0.02488 |
| Opus 5 | $0.00040 | $0.01244 |
| Sonnet 5 | $0.00016 | $0.00498 |
| Haiku 4.5 | $0.00008 | $0.00249 |
Grade A, and why
file-processor-subagent 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 9d 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 — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
File Processor Sub-Agent
Quand utiliser ce skill
Déléguer à ce sous-agent quand l'agent parent doit traiter des fichiers de formats variés sans polluer son contexte principal : ingestion de données, conversion de format, extraction de contenu (dont OCR), génération de rapports, traitement par lot d'un répertoire entier.
Ne pas utiliser si le fichier est < 5 Ko et que le format est trivial (JSON, YAML simple) : l'agent parent peut le lire directement.
Workflow en étapes
1. Validation des inputs
Avant toute opération, vérifier :
import os, pathlib
def validate_input(inp: dict) -> list[str]:
errors = []
fp = inp.get("file_path", "")
if not fp:
errors.append("file_path manquant")
elif not pathlib.Path(fp).exists() and inp.get("operation") != "generate":
errors.append(f"Fichier introuvable : {fp}")
if pathlib.Path(fp).stat().st_size > 500 * 1024 * 1024:
errors.append("Fichier > 500 Mo : utiliser batch + chunk_size")
if inp.get("operation") not in ("read","transform","generate","convert","batch","extract"):
errors.append("operation invalide")
return errors
Retourner un output_schema avec errors rempli si la validation échoue — ne jamais lever d'exception non catchée vers l'agent parent.
2. Détection du type de fichier
Ne pas faire confiance à l'extension seule.
import magic # python-magic
import chardet
def detect_file_type(path: str) -> tuple[str, str]:
mime = magic.from_file(path, mime=True) # ex: "application/pdf"
encoding = "binary"
if mime.startswith("text/"):
with open(path, "rb") as f:
raw = f.read(32_768)
encoding = chardet.detect(raw)["encoding"] or "utf-8"
return mime, encoding
Critères de sélection du parser :
| MIME détecté | Parser prioritaire | Fallback |
|---|---|---|
application/pdf |
pdfplumber |
PyMuPDF (fitz) |
application/vnd.openxmlformats-officedocument.spreadsheetml.sheet |
openpyxl |
pandas.read_excel |
application/vnd.ms-excel |
xlrd |
pandas.read_excel |
text/csv |
pandas.read_csv |
csv.DictReader |
application/vnd.openxmlformats-officedocument.wordprocessingml.document |
python-docx |
— |
application/json |
orjson |
json |
application/xml ou text/xml |
lxml.etree |
— |
text/html |
BeautifulSoup (lxml parser) |
— |
image/* |
Pillow + pytesseract (OCR) |
easyocr |
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.
- 9d ago First seen · 307 lines · 80 tokens per session scan A 1ce7591b67bc
file-processor-subagent is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 16d ago), licensed MIT. It adds 80 tokens to every session and 2,488 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 2026-08-30.
Other skills, from other repositories
steuer-assistent
Points to the standalone module steuer-assistent: a local, offline-first receipt worksheet for German employee income-related expenses (Werbungskosten) -- record, sum to the cent, private ZIP export. Use this skill when Werbungskosten receipts should be prepared in a structured way -- with a clear boundary: not tax…
finanz-versicherung
Strukturiert bereitgestellte Finanz- und Versicherungsunterlagen als neutrale Übersicht und Checkliste.
datapack-builder
Build professional financial services data packs from various sources including CIMs, offering memorandums, SEC filings, web search, or MCP servers. Extract, normalize, and standardize financial data into investment committee-ready Excel workbooks with consistent structure, proper formatting, and documented…
fsi-strip-profile
Creates professional investment banking strip profiles (company profiles) for pitch books, deal materials, and client presentations. Generates 1-4 information-dense slides with quadrant layouts, charts, and tables.
lbo-model
This skill should be used when completing LBO (Leveraged Buyout) model templates in Excel for private equity transactions, deal materials, or investment committee presentations. The skill fills in formulas, validates calculations, and ensures professional formatting standards that adapt to any template structure.
cim-builder
Skill "cim-builder" from w95/awesome-claude-corporate-skills, covering cim builder, workflow, step 1: gather source materials, step 2: cim structure and step 3: drafting guidelines.