file_reader

A skill for reading and summarizing text files such as Markdown, JSON, YAML, CSV, source code, and logs. It does not cover PDFs, Office files, images, or media.

In plain words
What is it for?
Use it to read local text files, inspect structured data, check file types, and summarize relevant sections of large logs or documents.
Why use it?
It provides a defined way to inspect text files without dumping unnecessary content or using the wrong file-handling method.

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/citedy/adclaw/file_reader
Any agent
npx skills add citedy/adclaw --skill file_reader
Clone the repo
git clone --depth 1 https://github.com/citedy/adclaw

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 425 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 94% copy Near-identical to another mod 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 $0.00041 $0.00425
Opus 5 $0.00020 $0.00212
Sonnet 5 $0.00008 $0.00085
Haiku 4.5 $0.00004 $0.00042

Measured 2d ago against content hash b68fda831a5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

file_reader 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.

Origin

This is a copy

94% identical to file_reader — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

src/adclaw/agents/skills/file_reader/SKILL.md · 62 lines

What it actually says

File Reader Toolbox

Use this skill when the user asks to read or summarize local text-based files. PDFs, Office documents, images, audio, and video are out of scope for this skill and should be handled by their dedicated skills/tools.

Quick Type Check

Use a type probe before reading:

file -b --mime-type "/path/to/file"

If the file is large, avoid dumping the whole content; extract a small, relevant portion and summarize.

Text-Based Files (use read_file)

Preferred for: .txt, .md, .json, .yaml/.yml, .csv/.tsv, .log, .sql, ini, toml, py, js, html, xml source code.

Steps:

  1. Use read_file to fetch content.
  2. Summarize key sections or show the relevant slice requested by the user.
  3. For JSON/YAML, list top-level keys and important fields.
  4. For CSV/TSV, show header + first few rows, then summarize columns.

Large Logs

If the file is huge, use a tail window:

tail -n 200 "/path/to/file.log"

Summarize the last errors/warnings and notable patterns.

Out of Scope

Do not handle the following in this skill (they are covered by other skills):

  • PDF
  • Office (docx/xlsx/pptx)
  • Images
  • Audio/Video

Safety and Behavior

  • Never execute untrusted files.
  • Prefer reading the smallest portion necessary.
  • If a tool is missing, explain the limitation and ask the user for an alternate format.
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 · 62 lines · 41 tokens per session scan A b68fda831a5e

Subscribe to this mod's changes

file_reader is a skill published in the GitHub repository citedy/adclaw (35 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 425 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to file_reader, differing in 11 lines, and is treated as a copy.