Claude Code logo
Claude Code template
docs.claude.com

Competitive Intelligence Digest

Snapshots competitors' public pages and reports only what changed, ranked by what it changes for you — and says so when nothing did. Public sources only.

NewNew8.8 KB snapshotStarter VM
Claude Code logo

What's inside

Harness

Claude Code

Plan

Starter

vCPU

1

Memory

2 GiB

Snapshot

8.8 KB

How it works · ~3 minutes

  1. 01 · Fork

    New isolated microVM on your subdomain — creator state included.

  2. 02 · Your keys

    Log into Claude Code with your own model credentials (BYOK).

  3. 03 · Ask it to work

    Open the terminal and give it a real job. You keep what ships.

30-day money-back on your first purchase · no free trial · keys never leave the VM

About this template

Nobody noticed the day their pricing page changed

Someone was assigned "keep an eye on the competition". They read three blog posts a week and forward one to Slack. Meanwhile the only change that mattered to every open deal went past unseen.

The diff is the product, not the snapshot

Anyone can read a competitor's pricing page. The value is knowing it changed on Tuesday.

So every source is snapshotted each run, and the digest reports only what differs, with both dates and the URL. A first run has no diff — it says so plainly, because a baseline narrated as news is manufactured significance.

Ranked by what it changes for you

  1. Pricing or packaging — hits every open deal today.
  2. A capability closing a gap you sell against — your battle card line is now wrong, and it says which line.
  3. Positioning shift — slow, but it changes who you're compared to.
  4. Hiring signal — weakest tier, reported as directional only. "Leaning into", never "they will ship X". A job posting is not a roadmap.

A competitor's blog post is not news, and cosmetic diffs get dropped.

Most weeks it says nothing changed

That's the correct answer, and it's why the digest is still being read in month three. A weekly intel report that finds something every week is manufacturing it.

It also names what it checked and found unchanged, so silence is confirmed rather than assumed.

Public sources only — and the reason is practical

Pricing, docs, changelog, status, careers, public reviews. Never a logged-in view, a trial account, a leaked screenshot, or something a customer shared in confidence.

Not squeamishness: intelligence from a private source can't be repeated to a prospect, cited in a deck, or defended. It's worthless the moment it matters, and a liability before that.

robots.txt checked first, one request per URL, and a blocked source stays blocked and is reported as such.

It prunes its own watchlist

If a URL hasn't changed in ten runs it says so and suggests dropping it. Watchlists only ever grow unless something forces the question.

What you supply

Your own Claude Code login. Nothing else — every source is a public page. List up to five URLs per competitor.

Where this stops

It watches and reports. It does not contact competitors, sign up for trials, or access anything gated.

It won't state their revenue, churn, runway or customer count, won't infer roadmap from hiring, won't explain why they made a change, and won't tell you a change is bad for them.

Verified on build: the skill, the working tree, the PUBLIC_SOURCES_ONLY guard, the diff-is-the-product rule, all four consequence tiers and the no-change rule are present on a fresh fork. Running it on your own competitors is yours to do.

Inside this fork

Forking copies this template into a brand-new, fully isolated microVM on your own subdomain. Here's exactly what lands in it.

  • Claude Code agent

    The upstream harness, pre-installed — same version the creator ran.

  • Starter VM

    1 vCPU · 2 GiB RAM · 10 GiB disk.

  • Creator's /persist data

    The captured persist volume is copied byte-for-byte into your fork.

  • BYOK — your keys, your VM

    Add your model API keys after forking; they live only inside your microVM.

What this agent can do

1 skill

  • competitive-digest

    Track competitors' public pages week over week and report only what changed, ranked by what it changes for you. Public sources only; never…

What you'll configure after forking

Secrets are scrubbed from shared templates — these are the names you supply in your agent's terminal once it boots.

Environment variables

  • ANTHROPIC_API_KEY

Your turn

Your own Competitive Intelligence Digest, live in about 3 minutes.

Forking copies this Claude Codeagent into a brand-new, fully isolated microVM on your own subdomain — the creator's /persist state and all. Add your own keys after it boots; they never leave the box. Don't love it? Your first jurniti purchase comes with 30 days to get every cent back.

New paid VM · BYOK · 30-day money-back on your first purchase · ~3 min to provision

Starter · fork

$25/ mo

Needs 1 of your own API key