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.
npx skills add getcargohq/cargo-skills --skill cargo-gtmgit clone --depth 1 https://github.com/getcargohq/cargo-skillsWrote 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.
[](https://agentmods.dev/skills/getcargohq/cargo-skills/cargo-gtm)<a href="https://agentmods.dev/skills/getcargohq/cargo-skills/cargo-gtm"><img src="https://agentmods.dev/badge/skills/getcargohq/cargo-skills/cargo-gtm/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/getcargohq/cargo-skills/cargo-gtm"><img src="https://agentmods.dev/badge/skills/getcargohq/cargo-skills/cargo-gtm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00441 | $0.08852 |
| Opus 5 | $0.00220 | $0.04426 |
| Sonnet 5 | $0.00088 | $0.01770 |
| Haiku 4.5 | $0.00044 | $0.00885 |
Grade B, and why
cargo-gtm scanned grade B with 1 finding 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 7d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- **Refuse and say why**: undifferentiated fan-out ("email everyone in `<industry>`"), contacting a suppressed record, filter evasion or disguised sender identity, auto-dialing and SMS blasts, batch-blasting LinkedIn eng How it starts
The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cargo GTM — Meta Skill
Use this skill for prospecting, account research, contact enrichment, verification, lead scoring, personalization, signal monitoring, and campaign activation.
Acceptable use — MANDATORY, before anything that touches a person
Full spec: references/acceptable-use.md. The short version, binding on every recipe here:
- B2B professional identities only, from the licensed providers in
provider-playbooks/— never consumer targeting, purchased lists, or data taken from a platform in breach of its terms. - Three checks before any outreach step — basis (customers, opted-in contacts, event attendees, or a documented legitimate-interest case), suppression (filter on unsubscribe / DNC / hard-bounce before enriching or sending), relevance (name, per recipient, why this message is for them). Any check that fails is a stop-and-ask, not a warning.
- Refuse and say why: undifferentiated fan-out ("email everyone in
<industry>"), contacting a suppressed record, filter evasion or disguised sender identity, auto-dialing and SMS blasts, batch-blasting LinkedIn engagement actions. Offer the compliant version once — state it, don't lecture. - This skill never sends. Outreach recipes stop at send-ready variables and hand off to the user's own sequencer, under that sequencer's limits, domains, and identities. Copy it drafts must carry an honest sender and subject, a working opt-out, and a postal address where the jurisdiction requires one.
Bootstrap
Already signed in (cargo-ai whoami returns a workspace)? Skip to the next section.
npm install -g @cargo-ai/cli # no global install? prefix every command with `npx @cargo-ai/cli`
cargo-ai login --email [email protected] # emailed code, no browser; creates the account on first use
# alternatives: --oauth (browser) · --token <api-token> (CI)
cargo-ai whoami # confirm the active workspace before any write
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/execution-plan-creator.md 6.0 KB
- agents/list-builder.md 2.6 KB
- guides/enriching-and-researching.md 7.5 KB
- guides/finding-companies-and-contacts.md 7.4 KB
- guides/writing-outreach.md 7.2 KB
- provider-playbooks/aiArk.md 12 KB
- provider-playbooks/anthropic.md 6.8 KB
- provider-playbooks/apolloio.md 7.1 KB
- provider-playbooks/bouncer.md 4.6 KB
- provider-playbooks/brightData.md 8.2 KB
- provider-playbooks/builtwith.md 5.2 KB
- provider-playbooks/cleon1.md 5.0 KB
- provider-playbooks/companyEnrich.md 5.1 KB
- provider-playbooks/contactOut.md 6.4 KB
- provider-playbooks/datagma.md 5.4 KB
- provider-playbooks/dropcontact.md 5.1 KB
- provider-playbooks/enrichCrm.md 5.4 KB
- provider-playbooks/enrichley.md 5.2 KB
- provider-playbooks/enrowio.md 5.2 KB
- provider-playbooks/exa.md 6.0 KB
- provider-playbooks/findyMail.md 5.1 KB
- provider-playbooks/firecrawl.md 6.0 KB
- provider-playbooks/forager.md 5.0 KB
- provider-playbooks/FullEnrich.md 5.7 KB
- provider-playbooks/g2.md 5.1 KB
- provider-playbooks/gemini.md 6.4 KB
- provider-playbooks/hunter.md 5.5 KB
- provider-playbooks/icypeas.md 6.3 KB
- provider-playbooks/kitt.md 4.2 KB
- provider-playbooks/leadMagic.md 5.2 KB
- provider-playbooks/linkedin.md 10 KB
- provider-playbooks/linkup.md 5.2 KB
- provider-playbooks/mixrank.md 4.7 KB
- provider-playbooks/neverBounce.md 4.8 KB
- provider-playbooks/oceanio.md 6.9 KB
- provider-playbooks/openAi.md 6.6 KB
- provider-playbooks/parallel.md 8.9 KB
- provider-playbooks/peopleDataLabs.md 8.9 KB
- provider-playbooks/perplexity.md 6.9 KB
- provider-playbooks/piloterr.md 5.7 KB
- provider-playbooks/prospeo.md 5.4 KB
- provider-playbooks/proxycurl.md 9.6 KB
- provider-playbooks/reverseContact.md 5.7 KB
- provider-playbooks/rocketreach.md 5.1 KB
- provider-playbooks/salesNavigator.md 5.8 KB
- provider-playbooks/serper.md 5.5 KB
- provider-playbooks/sillage.md 4.4 KB
- provider-playbooks/snitcher.md 5.6 KB
- provider-playbooks/societeInfo.md 5.6 KB
- provider-playbooks/theirStack.md 6.3 KB
- provider-playbooks/theSwarm.md 5.1 KB
- provider-playbooks/waterfall.md 6.7 KB
- provider-playbooks/x.md 6.8 KB
- provider-playbooks/zeroBounce.md 5.3 KB
- recipes/account-expansion.md 7.0 KB
- recipes/ads-audience-activation.md 12 KB
- recipes/build-tam.md 11 KB
- recipes/clay-to-cargo.md 14 KB
- recipes/custom-datapoints.md 29 KB
- recipes/funding-watch.md 6.6 KB
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.
- 7d ago Changed · +4 lines · +4 tokens per session db9c827f4df9
- 11d ago First seen · 287 lines · 437 tokens per session scan B a5d8dde850ef
cargo-gtm is a skill published in the GitHub repository getcargohq/cargo-skills (17 stars, last pushed today), licensed MIT. It adds 441 tokens to every session and 8,852 once invoked, about $0.0022 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
everme-memory
Use EverMe cloud memory proactively when the user refers to previous conversations, earlier decisions, "last time", "remember when", existing project conventions, or previously solved errors, and save durable user preferences, habits, and decisions the moment they are stated. Do not repeat a search when the host…
memory-tools
Use EverMe memory proactively when the user refers to previous conversations, earlier decisions, "last time", "remember when", existing project conventions, or previously solved errors, and save durable user preferences, habits, and decisions the moment they are stated. Do not repeat a search when a non-empty block…
memory-recall
Session-start primer that tells Kimi how EverMe's automatic cross-session memory works and how to treat the injected recall/profile context.
gtm-engineering
When the user wants to build GTM automation with code, design workflow architectures, use AI agents for GTM tasks, or implement the 'architecture over tools' principle. Also use when the user mentions 'GTM engineering,' 'GTM automation,' 'n8n,' 'Make,' 'Zapier,' 'workflow automation,' 'Clay API,' 'instruction stacks,'…
everme-memory
Persistent memory for Codex sessions with native lifecycle recall and save. Use EverMe proactively when the user refers to previous conversations, earlier decisions, "last time", "remember when", existing project conventions, or previously solved errors, or asks to continue prior work; save durable user preferences…
ai-cold-outreach
When the user wants to build an AI-powered outreach system, write cold emails, improve deliverability, or scale personalized outreach. Also use when the user mentions 'cold email,' 'cold outreach,' 'outreach automation,' 'Instantly,' 'Smartlead,' 'Clay,' 'email sequences,' 'deliverability,' 'personalization at scale,'…