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 runxhq/runx --skill nitrosendgit clone --depth 1 https://github.com/runxhq/runxWrote 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/runxhq/runx/nitrosend)<a href="https://agentmods.dev/skills/runxhq/runx/nitrosend"><img src="https://agentmods.dev/badge/skills/runxhq/runx/nitrosend/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/runxhq/runx/nitrosend"><img src="https://agentmods.dev/badge/skills/runxhq/runx/nitrosend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.02432 |
| Opus 5 | $0.00028 | $0.01216 |
| Sonnet 5 | $0.00011 | $0.00486 |
| Haiku 4.5 | $0.00006 | $0.00243 |
Grade A, and why
nitrosend 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nitrosend
Use this as the single public Runx surface for Nitrosend customer operations.
Local account runners bind the API key only to the local runtime. The hosted
review-content runner calls one bounded provider.read operation whose Cloud
adapter retains credential custody. No runner accepts an API key as skill input
or returns one in a receipt.
This skill is not for Nitrosend customer-support administration or team Slack work. Those are product-operator concerns owned by the Nitrosend repository.
Choose the runner
status(default): live account, brand, sender, domain, provider, warmup, and deliverability readiness.billing-status: read the current account subscription and eligible paid-plan catalog together. It creates no checkout; prepaid balance and add-funds readiness remain a distinctfundingblock in the status evidence.plan-checkout: re-read current billing and plans, approve one exact plan, create the idempotent hosted checkout or confirmed in-place plan change, then read billing again. A checkout URL is pending operator work, not proof of payment or activation.plan-checkout-status: reconcile one returned plan-purchase ID without creating another checkout. Use it after hosted approval, timeout, or an ambiguous client response.configure-sender: read, approve, update, and independently read back one explicitly selected brand's exact sender defaults. It configures no content, audience, campaign, flow, or delivery.analytics: live account, campaign, flow, or message insights.review-delivery: read-only content and preflight review. Flow review requires the exact immutablerevision_id; campaigns and templates do not.review-content: read-only spam and accessibility review for bounded inline email content. It accepts no account entity, audience, delivery, or mutation input and is safe to compose behind a payment-as-access vendor endpoint.plan-campaign,plan-flow,plan-transactional, andplan-import: bounded agent judgment that produces a reviewable request without provider completion.compose-email: read the live Nitrosend authoring contract, let one bounded agent author its exact next call, and return authoritative MCP validation. It never persists a draft or gains delivery authority.apply-draft: apply exact reviewed arguments for a campaign, flow, template, segment, or remote image ingest. Image ingest validates the remote bytes and returns a durable Nitro-hosted brand-library URL. It never sends or activates.approve-delivery: approve a reviewed campaign or an exact flow revision without delivering.send-campaign: send or schedule an already-approved campaign after a fresh provider review and explicit approval.activate-flow: publish an exact already-approved flow revision after a fresh review and explicit approval.send-transactional: dry-run or send one idempotent message to one recipient.import-contacts: dry-run or import at most 100 inline consented records.import-contacts-csv: validate or upload a local CSV through Nitrosend's authorized direct-upload path. File bytes and signed URLs never enter the agent packet or receipt.import-status: make one bounded status read for an asynchronous import.segment-from-prose: internal planning lane for the current supported filter catalog; unsupported filters are rejected rather than approximated.
What ships with it
31 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.
- fixtures/analytics-scope-needs-input.yaml 285 B
- fixtures/billing-status-returns-status-and-plans.yaml 2.7 KB
- fixtures/configure-sender-rejects-blank-idempotency.yaml 594 B
- fixtures/consented-contact-import-ready.yaml 2.0 KB
- fixtures/default-requires-account-binding.yaml 939 B
- fixtures/newsletter-template-ready.yaml 2.3 KB
- fixtures/plan-checkout-approved-through-readback.yaml 3.6 KB
- fixtures/plan-checkout-requires-approval.yaml 2.2 KB
- fixtures/plan-checkout-status-reuses-purchase.yaml 1.5 KB
- fixtures/raw-html-template-needs-input.yaml 1.1 KB
- fixtures/reject-flow-automation-ask.yaml 1.6 KB
- fixtures/reject-flow-one-off-broadcast.yaml 1.5 KB
- fixtures/reject-purchased-contact-list.yaml 1.2 KB
- fixtures/reject-transactional-broadcast.yaml 1.2 KB
- fixtures/review-content-ready.yaml 1.6 KB
- fixtures/scheduled-campaign-ready.yaml 3.3 KB
- fixtures/segment-prose-ready.yaml 1.3 KB
- fixtures/segment-unsupported-history-rejected.yaml 1.2 KB
- fixtures/transactional-order-confirmation-ready.yaml 1.7 KB
- fixtures/welcome-flow-ready.yaml 2.4 KB
- graph/provider-operation/nitro-manage-billing.input-schema.json 2.3 KB
- graph/provider-operation/nitrosend-operation.mjs 21 KB runs code
- graph/provider-operation/nitrosend-operation.test.mjs 22 KB runs code
- graph/provider-operation/SKILL.md 562 B
- graph/provider-operation/X.yaml 7.4 KB
- review-content.mjs 4.5 KB runs code
- review-content.test.mjs 1.4 KB runs code
- tools/nitrosend/bulk_import/manifest.json 1.6 KB
- tools/nitrosend/bulk_import/run.mjs 11 KB runs code
- tools/nitrosend/bulk_import/run.test.mjs 7.9 KB runs code
- X.yaml 48 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.
- 5d ago First seen · 216 lines · 56 tokens per session scan A a7e68ef11f9e
nitrosend is a skill published in the GitHub repository runxhq/runx (84 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 2,432 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
dd-synthesis
Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.
dd-report-format
Standard output format for due diligence analysis reports. Use when producing your final analysis to ensure consistency across all specialist agents.
dd-risk-scoring
Calculate weighted risk scores from specialist agent reports. Use when synthesizing multiple due diligence reports into an overall investment risk assessment.
dd-sourcing
Document sources properly for due diligence reports. Use when citing any external data, ensuring full traceability and auditability of findings.
dd-verification
Verify claims in pitch decks and founder statements using multiple independent sources. Use when analyzing any claim about market size, traction, team background, or competitive positioning.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.