file-reading

A file-reading router that chooses instructions for common file types such as PDF, Word, PowerPoint, Excel, text, CSV, and JSON files.

In plain words
What is it for?
Use it as the starting point when asked to read or summarise an uploaded file of unknown type.
Why use it?
It removes the need to know which reader or extraction method each file format requires.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/decocms/studio/file-reading
Any agent
npx skills add decocms/studio --skill file-reading
Clone the repo
git clone --depth 1 https://github.com/decocms/studio

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 315 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00046 $0.00315
Opus 5 $0.00023 $0.00158
Sonnet 5 $0.00009 $0.00063
Haiku 4.5 $0.00005 $0.00032

Measured 2d ago against content hash 413852cc1ab4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

file-reading 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 2d 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.

packages/sandbox/image/skills/file-reading/SKILL.md · 24 lines

What it actually says

file-reading — router by file type

When asked to read or summarize a file, dispatch by extension to the appropriate skill under org/public/core/:

Extension Skill Script
.pptx pptx python org/public/core/pptx/extract.py
.docx docx python org/public/core/docx/extract.py
.xlsx xlsx python org/public/core/xlsx/extract.py
.pdf pdf python org/public/core/pdf/extract.py
.txt, .md cat
.csv cat (or column -t -s, for alignment)
.json cat (or jq . if structure matters)

For extensions not listed, read the corresponding SKILL.md under org/public/core/ if one exists, otherwise fall back to file <path> to identify the format and proceed manually.

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. 2d ago First seen · 24 lines · 46 tokens per session scan A 413852cc1ab4

Subscribe to this mod's changes

file-reading is a skill published in the GitHub repository decocms/studio (402 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 315 once invoked, about $0.0002 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.