cargo-execution-planner

cargo-execution-planner is an agent for Claude Code from getcargohq/cargo-skills. It costs 99 tokens per session (435 once invoked), scanned A, original, MIT.

An agent that creates a staged, priced execution plan for Cargo GTM actions without running paid actions. Cargo GTM is a system for carrying out go-to-market tasks through connected data providers.

In plain words
What is it for?
Use it to plan multi-stage GTM runs, check connected providers and account balance, test batch actions with samples, and reconcile the estimated cost.
Why use it?
It shows the steps, available providers, sample records, credit costs, and budget impact before paid work begins.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the cargo plugin — 19 skills, 2 agents shipped together

Good fit Use it to plan multi-stage GTM runs, check connected providers and account balance, test batch actions with samples, and reconcile the estimated cost.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/getcargohq/cargo-skills/cargo-execution-planner
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.

Clone the repo
git clone --depth 1 https://github.com/getcargohq/cargo-skills

Made for: Claude Code.

Or install cargo, the plugin that ships this one along with the rest of its 19 skills, 2 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cargo-execution-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/getcargohq/cargo-skills/cargo-execution-planner.svg)](https://agentmods.dev/agents/getcargohq/cargo-skills/cargo-execution-planner)
Your own site
<a href="https://agentmods.dev/agents/getcargohq/cargo-skills/cargo-execution-planner"><img src="https://agentmods.dev/badge/agents/getcargohq/cargo-skills/cargo-execution-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 435 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00099 $0.00435
Opus 5 $0.00049 $0.00217
Sonnet 5 $0.00020 $0.00087
Haiku 4.5 $0.00010 $0.00044

Measured 8d ago against content hash c154a7ca1485, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cargo-execution-planner 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 8d 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.

agents/cargo-execution-planner.md · 20 lines

What it actually says

You are the Cargo execution planner. You produce a costed, stage-by-stage GTM execution plan; you never execute paid actions yourself.

First, locate and read your full instructions and grounding (the skills are installed alongside this plugin — find them with Glob):

  1. **/cargo-gtm/agents/execution-plan-creator.md — your role spec and the exact plan format (goal restatement → operational assumptions → stage breakdown with provider+action slugs and costs → sample step + budget reconciliation → shaped choices). Follow it precisely.
  2. **/cargo-gtm/references/cost-discipline.md — the mandatory sample → approval → full-run gate your plan must embody. Any step that fans out as a batch samples 10–20 records first, and the approval question states both the record count and the credit estimate.
  3. **/cargo-gtm/references/credits-cost-table.md and **/cargo-gtm/references/stage-action-map.md — the only sources for action costs. Never invent a cost.

Bash is for read-only grounding only: cargo-ai billing subscription get (balance), cargo-ai connection connector list / integration get <slug> (what's actually connected and available). If a needed provider is not connected, the plan must say so and offer the connected alternative from the stage-action-map.

Return the plan in the exact format the role spec defines — the parent session relays it into the approval gate unchanged.

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. 8d ago First seen · 20 lines · 99 tokens per session scan A c154a7ca1485

Subscribe to this mod's changes

cargo-execution-planner is an agent published in the GitHub repository getcargohq/cargo-skills (17 stars, last pushed 2d ago), licensed MIT. It adds 99 tokens to every session and 435 once invoked, about $0.0005 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.