agent-intent-from-docs

A command that creates a specialised agent by studying documentation pages and following a stated purpose. The first argument describes the purpose, and the remaining arguments are documentation URLs.

In plain words
What is it for?
Use it to create agents for focused jobs such as planning a migration between documented services.
Why use it?
It avoids manually reading several documentation pages and turning them into instructions for a new agent. Multiple pages can be researched separately before their findings are combined.

Command for Claude Code

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 commands/nodnarbnitram/claude-code-extensions/agent-intent-from-docs
Clone the repo
git clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensions

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,320 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 $0.00011 $0.01320
Opus 5 $0.00005 $0.00660
Sonnet 5 $0.00002 $0.00264
Haiku 4.5 $0.00001 $0.00132

Measured 2d ago against content hash 2d52ff4848ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-intent-from-docs 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.

.claude/commands/agent-intent-from-docs.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Agent from Documentation with Intent

You will create a new specialized agent by analyzing documentation from the provided URLs, guided by a specific intent or purpose.

Arguments: $ARGUMENTS

Important: The first argument is the intent/description of what the agent should do. All remaining arguments are documentation URLs to analyze.

Your Task

Follow these steps to create the agent:

Step 1: Parse Arguments

Extract from $ARGUMENTS:

  • Intent: The first argument (everything in quotes or up to the first URL)
  • Documentation URLs: All remaining arguments

The intent describes the specific purpose or use case for this agent (e.g., "Create a migration assistant agent from incident.io and opsgenie to betterstack").

Step 2: Analyze Documentation

If multiple URLs are provided, launch multiple technical-researcher agents in parallel (one per URL). If only one URL is provided, use a single researcher.

For parallel execution with multiple URLs:

  • Launch all technical-researcher agents simultaneously in a single message with multiple Task tool calls
  • Each agent should analyze its assigned URL independently
  • Combine all research findings before proceeding to Step 3

Each researcher should investigate with the intent in mind:

  • What technology/framework/library is being documented
  • Key concepts, APIs, methods, and patterns relevant to the stated intent
  • Best practices and conventions
  • Common workflows and use cases that align with the intent
  • Important implementation details that an expert should know
  • Migration paths, comparison features, or integration points if relevant to the intent
  • How this technology differs from alternatives

Request a comprehensive summary suitable for creating a specialized agent focused on the stated intent.

Step 3: Determine Agent Creation Strategy

After gathering all research findings, analyze whether to create one or multiple agents:

Create MULTIPLE agents when URLs represent distinct verticals/technologies:

  • Different core APIs or services (e.g., Cloudflare Workers vs D1 vs R2)
  • Separate deployment models or runtime environments
  • Distinct problem domains within a platform
  • Independent tools/products that happen to share a brand

Read the full file on GitHub · 128 lines

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 · 128 lines · 0 tokens per session scan A 2d52ff4848ef

Subscribe to this mod's changes

agent-intent-from-docs is a command published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 1,320 once invoked, about $0.0001 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.