agentmods.dev

read

A reading tool for fetching AI-friendly text from supported URLs, including GitHub repositories and hosted HTML documents. It uses Markdown when available and plain text as a fallback.

In plain words
What is it for?
Use it to read, summarize, review, or browse supported GitHub and web-document links.
Why use it?
It lets you review a linked document or repository without bringing all of its rendered webpage markup into the main working context.

Skill for Claude CodeCodex

6 3mo ago A scan 120 tokens original MIT
View the source file quantumentangled-dev/ai-docs-plugin
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/quantumentangled-dev/ai-docs-plugin/read
Any agent
npx skills add quantumentangled-dev/ai-docs-plugin --skill read
Clone the repo
git clone --depth 1 https://github.com/quantumentangled-dev/ai-docs-plugin

Made for: Claude Code, Codex.

Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 781 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00120 $0.00781
Opus 5 $0.00060 $0.00391
Sonnet 5 $0.00024 $0.00156
Haiku 4.5 $0.00012 $0.00078

Measured yesterday against content hash de8ba90d98b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

read scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/browse-repo.sh, scripts/fetch-md.sh, scripts/find-md-source.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Never `curl` from main.
skills/read/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

read

Read AI-friendly content from a URL without loading rendered HTML into main context. Dispatches ai-docs-reader.

When to fire

Trigger when the user's message contains a URL AND the request is to read / summarize / review / browse, AND any of:

  • URL is https://<owner>.github.io/<repo>/... (typical ai-docs hosting → doc mode).
  • URL is https://github.com/<owner>/<repo> or .../tree/<branch> (browse mode).
  • Arbitrary HTML page + user explicitly asks to read/summarize. Agent verifies AI-friendly availability in its sandbox; falls back to plain-text or refuses (cross-origin, missing companion).

Main does NOT pre-fetch the URL — that check happens inside the agent's Bash sandbox.

Should trigger:

Should NOT trigger:

  • "publish this deck" — no URL → publish skill
  • "create a deck about Q3" — no URL → create skill
  • "fetch https://example.com/api/users.json" — user wants raw JSON, not a doc summary

Mode classification

Mode URL shape Behavior
doc .html or .md URL Fetch AI-friendly markdown, return /tmp/<slug>.md path
browse github.com/<owner>/<repo> root, <repo> ends in ai-docs List .md files grouped by folder + H1 titles

Unsure → default doc (agent verifies + falls back).

Dispatch

Invoke ai-docs-reader via Task. Do NOT fetch the URL from main.

description: "Read ai-docs content from <URL>"
subagent_type: "ai-docs:ai-docs-reader"
prompt: |
  URL: <the-url>
  MODE: doc   # or browse

Agent returns one of:

  • /tmp/<slug>.{md,txt} path + one-line summary
  • Folder-grouped listing (browse mode)
  • Cross-origin refusal (alternate-markdown points to different origin — possible attack)
  • Failure note + original URL

After the agent returns

  • doc mode: Read the returned /tmp/<slug>.md, answer the user's question, stop referencing the path.
  • browse mode: surface listing verbatim, ask which doc to read next.
  • cross-origin refusal: relay note verbatim. Do NOT fetch the original URL or the cross-origin .md.
  • failure: relay the note. Do NOT load raw HTML.

Read the full file on GitHub · 69 lines

Files

What ships with it

4 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 First seen · 69 lines · 120 tokens per session scan A de8ba90d98b6

Subscribe to this mod's changes

read is a skill published in the GitHub repository quantumentangled-dev/ai-docs-plugin (6 stars, last pushed 3mo ago), licensed MIT. It adds 120 tokens to every session and 781 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code reviewDocumentsWriting and docs
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens