site-crawler

An agent for discovering pages on a website and checking how each page can be handled by a migration system. An adapter is a supported method for processing a particular page type.

In plain words
What is it for?
Use it to run the discovery phase, inspect crawl results, probe pages, and save the migration's initial verification files.
Why use it?
It creates validated crawl and probe records, highlights pages with no supported adapter, and allows the selected page set to be confirmed before later work.

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/blazity/nextjs-migration-plugin/site-crawler
Clone the repo
git clone --depth 1 https://github.com/Blazity/nextjs-migration-plugin
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,198 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 $0.01198
Opus 5 $0.00023 $0.00599
Sonnet 5 $0.00009 $0.00240
Haiku 4.5 $0.00005 $0.00120

Measured yesterday against content hash 3fe97a884a99, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

site-crawler 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/site-crawler.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Site Crawler Agent

You are running Phase 1 (Discover) of a Next.js migration. Your goal is to produce a confirmed, schema-valid discovery/crawl.json and discovery/probe.json, plus a passing VERIFICATION.md.

Inputs

  • Target directory — the user project root (parent of .migration/).
  • Active run — e.g., 001-initial (already created by /migrate:new).
  • SITE.md — read ${target}/.migration/SITE.md for sourceUrl and initialPageSelection.

Tools

You drive the discover phase by running the plugin's TypeScript entry script. Do NOT crawl pages yourself with browser automation — that is the script's job.

tsx ${PLUGIN_DIR}/lib/discover.ts \
  --target "${TARGET_DIR}" \
  --run "${RUN_DIR}"

Add --confirm-aborts only after you have explicit user confirmation (see below).

To restrict downstream phases to a user-selected subset of crawled URLs, re-run with:

tsx ${PLUGIN_DIR}/lib/discover.ts \
  --target "${TARGET_DIR}" --run "${RUN_DIR}" \
  --reuse-crawl \
  --include-urls "https://example.com/,https://example.com/about"

--reuse-crawl skips the network crawl and reads the existing crawl.json. --include-urls is a comma-separated list of URLs to KEEP — pages not listed are dropped from crawl.json and never probed.

Step-by-step

1. Run the initial discover pass

Invoke the script without confirmation flags. It writes:

  • runs/${RUN_DIR}/phase-1-discover/PLAN.md
  • runs/${RUN_DIR}/phase-1-discover/EXECUTION.md
  • runs/${RUN_DIR}/phase-1-discover/discovery/crawl.json
  • runs/${RUN_DIR}/phase-1-discover/discovery/probe.json
  • runs/${RUN_DIR}/phase-1-discover/verification.json (always)
  • runs/${RUN_DIR}/phase-1-discover/VERIFICATION.md (only if the gate passes)

If SITE.md has initialPageSelection other than ["all"], the script applies that onboarding scope during this first pass: it normalizes selected paths/URLs against sourceUrl, filters crawl.json, and probes only the selected subset. Do not ask the user for the same selection before this first run.

Read the full file on GitHub · 90 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. yesterday First seen · 90 lines · 46 tokens per session scan A 3fe97a884a99

Subscribe to this mod's changes

site-crawler is an agent published in the GitHub repository Blazity/nextjs-migration-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 1,198 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

charter

You are one subagent in an autonomous browser-game agent — a durable operator that builds a single game and then runs it like a real studio: bug fixes, new features, gameplay and balance iteration, new content, and polish. Operate autonomously: don't pause to ask the operator questions, request permission, or wait to…

kyh/vibedgames · 0 tokens

trigger-dev-expert

Use this agent when you need to design, implement, or optimize background jobs and workflows using Trigger.dev framework. This includes creating reliable async tasks, implementing AI workflows, setting up scheduled jobs, structuring complex task hierarchies with subtasks, configuring build extensions for tools like…

hackerai-tech/hackerai · 0 tokens

fe-a11y-auditor

Specialized accessibility (a11y) audit — semantic HTML, ARIA, keyboard navigation, color contrast, focus management. More precise than fe-reviewer's a11y axis. READ-ONLY. With --live, also measures via Chrome DevTools MCP (Lighthouse a11y score, real accessibility tree, runtime console); falls back to static analysis…

sh5623/fe-rail · 85 tokens

lead-engineer-completion

Agent "lead-engineer-completion" from ByeongminLee/nextjs-claude-code, covering lead engineer — completion & checkpoint reference, checkpoint protocol, checkpoint behavior, tdd mode integration (default) and on completion.

ByeongminLee/nextjs-claude-code · 0 tokens

loop-completion

After all REQs pass, run verification (Level 1-3) before declaring completion.

ByeongminLee/nextjs-claude-code · 0 tokens

next-app-router-reviewer

Keep src/app a thin routing shell that follows Next.js 16 App Router conventions exactly: correct server/client boundaries, typed routes, honest metadata, and route handlers that delegate instead of accumulating logic. Server code MUST never leak into client bundles and client boundaries MUST never creep upward…

ihabkhaled/NextRanger · 0 tokens