Office hours: Build your self-driving GTM engine·Oct 29, 9:00am PT, onlineRegister→
Cargo
  • PrimitivesData ModelsYour companies, contacts and deals, merged from every sourceContextWhat your team knows, as files every agent readsTerritoriesWho sells where, defined onceMailboxesMailboxes in your reps' names, warmed up and kept under limitsToolsThe actions your agents, plays and reps callAgentsAI that researches, decides and writes, reading your contextPlaysWorkflows that run on a trigger or a schedule, with retriesAppsInternal apps for your reps, hosted on Cargo
    Add-onsChrome ExtensionSell faster, right in your browserButtonTrigger AI agents inside your CRMFormTurn any tool into an embeddable formSlackTag Cargo in Slack. It does the GTM workGitHubPlan on every pull request, deploy on merge
    MoreProjectsDefine your entire GTM in codeCLIUse Cargo from your terminalMCPUse Cargo from Claude and ChatGPTDeveloper resourcesCargo API docs, OpenAPI spec, auth docs, webhooks, MCP serverAPI ReferenceExplore the Cargo APIDocumentationLearn how to use CargoIntegrationsConnected to your entire GTM stack
  • VeriffHow Veriff replaced MuleSoft with Cargo under NetSuite, Stripe and SalesforceAugmentHow Augment Code routes developer sign-ups to reps in under an hourWeights & BiasesHow Weights & Biases ships a new purchase signal in 2 days on CargoSee all
  • Pricing
  • Cookbooks
  • Blog
Sign in
Cookbooks
WCContext

Web capture

Keep your company context current from your website and competitors' pages: each Monday your site, competitors' pages and news about both land in context/ as one pull request; the first run seeds positioning, offerings, an inferred ICP with a disqualifier, competitors, clients and proof, and every later run adds a dated note of what changed, never editing an existing file.

Installation
Set up the web-capture cookbook in this project. 1. If the Cargo CLI is not installed yet, follow every step in https://api.getcargo.io/INSTALL.md 2. From the Cargo project, run: cargo-ai project add cookbook/web-capture 3. Then follow .claude/skills/web-capture/SKILL.md. Stop for my approval before any paid call, and stop at "cargo-ai project plan" before deploying anything.
Paste it into Claude Code, Cursor, Codex, Gemini CLI, Devin or Replicas.
$cargo-ai project add cookbook/web-capture
Run it in your Cargo project. Copies the example in, and deploys nothing.

Say this to your agent

Every Monday, read our website, our competitors' pricing and changelog pages, and the news about all of us, and keep context/ current.

Illustrative output #

Fictional records, to show the shape of what comes back.

text
insight/2026-10-05-web.md
- Northwind: new "Enterprise" tier on /pricing, with SSO and audit logs [R: https://northwind.example/pricing]
- Northwind: raised a $20M Series B led by Contoso Ventures, 2026-10-01 [R: https://news.example/northwind-series-b]
- Northwind: Fabrikam named as a customer, 40% faster onboarding [R: https://northwind.example/customers/fabrikam]
- Tailspin (competitor): Team plan price up from $49 to $69 a seat [R: https://tailspin.example/pricing]

client/fabrikam.md, proof/fabrikam-onboarding.md   (reference_permission: unknown)
PR body: proposes adding "Enterprise" to global/offerings.md and the new price to alternative/tailspin.md

A week after the first run: one pull request, four findings across two companies, two new files, two proposed edits, and two reads billed (the pages and the news).

Done when #

  • DOMAIN, PAGES and COMPETITORS name the company, its real sections and the competitors worth watching, and the contract passes
  • cargo-ai project check prints the agent bound to the repository root, and cargo-ai project plan reports one agent, two bound connectors, one folder and no model
  • the first run opened one pull request with the page, competitor and news files, seeded every empty domain, and edited no existing file
  • every seeded file carries tags, icp/ names a disqualifier, and every client/ file carries reference_permission: unknown
  • after the baseline was merged, a run with a change opened a pull request adding insight/<date>-web.md with one tagged line per finding, each naming its company, and proposed rather than made any edit to an existing file
  • a run with nothing worth writing opened no pull request
  • after merging and cargo-ai project deploy, a seeded file is readable from the workspace context repository and an agent with the context capability quotes it back with its tag

What it costs #

Fetch live prices before every estimate: cargo-ai connection integration get parallel, plus the LLM connector’s model. Quote the lookup time with the estimate.

Each run bills two reads: one parallel.extract over every listed URL, the company’s and the competitors’ (billed per URL, a 404 included), and one parallel.createTask on the lite processor, the cheapest rung of its price ladder. Plus the harness run, which scales with how much changed.

To keep your positioning, ICP and competitor notes current, read your own site, your competitors’ pages and recent news about both every week, and let git show what changed. This cookbook runs one Claude Code harness agent each Monday and lands the result in context/ as one pull request: the first run seeds the files, and every later run adds a dated note of what changed and never edits an existing file.

shellscript
cargo-ai project add cookbook/web-capture

What it does #

  • Reads the web, the same way every week. Two cargo-ai commands generated in the prompt: one parallel.extract with fullContent over the company’s own pages and each competitor’s watched pages, and one parallel.createTask news question about all of them for the days since the last merged read. A fixed node -e line writes each page to cadence/log/raw/web/pages/<page>.md or cadence/log/raw/web/competitors/<competitor>/<page>.md, and the news to cadence/log/raw/web/news/<date>.json. No text passes through the agent on its way to disk.
  • Lets git say what changed. git diff against the default branch shows which pages changed; a news URL not in an earlier file is new.
  • Seeds once. The first run fills every empty context/ domain: global/, icp/ with a disqualifier, alternative/, client/, proof/, signal/. Every sentence tagged [R], [I] or [TR].
  • Adds what changed. Every run after writes one dated insight/<date>-web.md, each line naming its company, plus a file for a newly named customer or competitor. It never edits a file that exists; a change to one is a proposal in the pull request body.
  • Stops. One pull request, never merged, or none in a quiet week. Nothing here reads a CRM, a call or Slack.

Adds 4 resources and no script.

FileResourceRole
infra/agents/web-scribe.tsdefineAgent (claudeCode)the scribe: model, folder, weekly cron, no env
infra/agents/web-scribe.prompt.ts(not a resource)the whole procedure: domain, pages, competitors, the exact commands, the rules
infra/connectors/anthropic.tsdefineConnector (anthropic)the model the harness runs on, billed and metered
infra/connectors/git.tsdefineConnector (github)the clone, branch, push and PR path, resolved by binding
infra/folders/index.tsdefineFolderthe workspace folder the agent is filed in

Why no script #

The other capture cookbooks read their source with a committed collector, because a fetch loop an agent re-derives each week silently changes shape. Here the reads are two fixed commands, so the prompt carries them exactly, and git already does the one thing a collector would add: comparing this week to the last. What keeps the comparison honest is mechanical: fullContent returns the whole page rather than excerpts chosen for a question, and a node -e line writes the files from the command output, so the agent never retypes a page. Both were checked live: two reads of the same pages a minute apart were byte-identical.

Why competitors are in the default #

A company already knows its own launches, pricing and funding; it made them. What a weekly read catches that the team does not already know is a competitor changing its pricing or shipping something. Same two reads, one more set of URLs, and the findings land in insight/ with the competitor’s name and in proposals against its alternative/ file.

Why the baseline is the last merged read #

The harness clones the default branch, so the only read a run can diff against is one that was merged. A quiet week opens no pull request and commits nothing, which is why the news window starts at the date of the last commit under cadence/log/raw/web/ rather than a fixed seven days: the next run covers the gap. It is also why the first run always opens a pull request, even when every domain was already seeded.

Why one source #

A cookbook is a prebuilt approach an agent follows. Give it a page and a deal in one run and the reader cannot tell the two confidence levels apart afterwards. So this cookbook holds one: what is public, tagged as such. The CRM has win-loss-review, which verifies the ICP this seeds; calls have call-capture.

Placeholders (edit before deploy) #

  1. DOMAIN, PAGES and COMPETITORS in infra/agents/web-scribe.prompt.ts. The agent refuses the placeholder domain; COMPETITORS ships empty.
  2. languageModel on the agent.

What it does not do #

It does not read a CRM, a call, an inbox or Slack; write the workspace context directly; edit a file that exists; write a page by hand; contact anyone; or merge its own pull request.

Verify #

From this skill’s folder:

shellscript
node --import tsx evals/contract.mjs

From the project root:

shellscript
npm run check && cargo-ai project plan
Version0.2.0
LicenseMIT
Source
Deploys
  • agents
  • connectors
For
  • GTM engineering
  • RevOps
  • Marketing
Integrations
  • Anthropic
  • GitHub
Content
  • Say this to your agent
  • Illustrative output
  • Done when
  • What it costs
  • What it does
  • Why no script
  • Why competitors are in the default
  • Why the baseline is the last merged read
  • Why one source
  • Placeholders (edit before deploy)
  • What it does not do
  • Verify
More in Context
  • Call capture
  • Win loss review
Next: Fundamentals
  • TAM building
  • TAM building advanced
  • Account scoring
  • Contact sourcing
  • Website building
  • Website auditing

Build the self-driving GTM engine

Your coding agents build it on Cargo.Or our team builds, operates and improves it with you.

Start building
Cargo
Backed byY CombinatorSOC 2 Type IICertified
LinkedinX

Product

Data ModelsContextTerritoriesMailboxesToolsAI AgentsPlaysAppsIntegrationsPricing

Add-ons

Chrome extensionButtonFormSlackGitHub

Build

DocsDeveloper resourcesCargo API docsCargo OpenAPI specCargo auth docsCargo webhooksCargo MCP serverProjectsClaude CodeCodexCursorAll coding agents

Resources

ReportsBlogCustomer storiesCookbooksEnrichmentRoutingSignalsScoringCRM hygieneAd audiencesGTM skillsGTM EngineeringGlossaryCompareCargo x ClayCargo x WorkatoCargo x n8nCargo x DeeplineCargo x DefaultCargo x LeanDataCargo x UnifyCargo x ValleyCargo x GojiberryCargo x PhantomBusterCargo x ZapierCargo x ApolloCargo x Chili PiperCargo x Common RoomCargo x MakeCargo x Tray.io

Company

ManifestoCommunityEventsJobsPartners DirectoryPartner Program

Legal

SecurityTerms of servicePrivacy PolicyRefundsDPASupport
© 2026 Cargo
 ////////    ///////    ////////     ////////    ///////
///         ///   ///   ///   ///   ///         ///   ///
///         ///   ///   ///   ///   ///         ///   ///
///         /////////   ////////    ///  ////   ///   ///
///         ///   ///   /// ///     ///   ///   ///   ///
///         ///   ///   ///  ///    ///   ///   ///   ///
 ////////   ///   ///   ///   ///    ///////     ///////

$ npm install -g @cargo-ai/cli