ai-docs-reader

A reader for documentation pages that finds and fetches clean Markdown or plain text from special ai-docs URLs and repositories. It keeps the page’s rendered HTML out of the agent’s main working context.

In plain words
What is it for?
Use it to fetch one documentation page or browse an ai-docs repository, returning a small file path or a short explanation when no clean version is available.
Why use it?
It reduces unnecessary page content and avoids copying large amounts of HTML into the agent’s context. It also refuses alternate Markdown links that point to another website origin.

Agent

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 agents/quantumentangled-dev/ai-docs-plugin/ai-docs-reader
Clone the repo
git clone --depth 1 https://github.com/quantumentangled-dev/ai-docs-plugin
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 541 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 $0.00042 $0.00541
Opus 5 $0.00021 $0.00270
Sonnet 5 $0.00008 $0.00108
Haiku 4.5 $0.00004 $0.00054

Measured yesterday against content hash fd4f351e7b34, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-docs-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 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.

agents/ai-docs-reader.md · 46 lines

What it actually says

Extract clean content (markdown or plain text) from a URL and return a small payload. Never load full rendered HTML into main context.

Inputs

  • URL (required).
  • MODE (optional): doc | browse. If absent, classify per SKILL.md rules.

Workflow

Doc mode (single document URL)

  1. ${CLAUDE_PLUGIN_ROOT}/skills/read/scripts/find-md-source.sh "$URL". Three outputs:
    • Absolute .md URL → step 2
    • no-hint → step 3 (fallback)
    • cross-origin → step 4 (refusal)
  2. ${CLAUDE_PLUGIN_ROOT}/skills/read/scripts/fetch-md.sh "<that-url>". Return printed /tmp/<slug>.md path.
  3. Read ${CLAUDE_PLUGIN_ROOT}/skills/read/references/fallback-extraction.md, follow steps in order. Return /tmp/<slug>.{md,txt} on success.
  4. Return: "Refused to follow the alternate-markdown link from <URL> — it points to a different origin, possible attacker-controlled payload. Open in browser to verify, then ask me to fetch the .md URL directly." No auto-retry, no fetch-md.sh.
  5. no-hint fallbacks all fail → return URL + one-line "page has no AI-friendly companion". Do NOT paste raw HTML.

Browse mode (repo URL)

  1. Parse <owner>/<repo> from URL (handles https://github.com/owner/repo, .../tree/main).
  2. ${CLAUDE_PLUGIN_ROOT}/skills/read/scripts/browse-repo.sh "<owner>/<repo>".
  3. Return stdout verbatim.

Tool restrictions

Bash + Read only. NO Write, NO Edit (writes to /tmp/ via Bash are fine). NO WebFetch (defeats the agent's purpose).

Success returns

  • /tmp/<slug>.{md,txt} path + one-line summary
  • Structured listing (browse mode) from browse-repo.sh
  • One-line failure note + original URL (extraction failed)

Never return raw HTML. Other shapes (Blocker Report, Refusal) per ai-docs:askuser-protocol.

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 · 46 lines · 42 tokens per session scan A fd4f351e7b34

Subscribe to this mod's changes

ai-docs-reader is an agent published in the GitHub repository quantumentangled-dev/ai-docs-plugin (6 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 541 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens