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 send-asgit 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/send-as)<a href="https://agentmods.dev/skills/runxhq/runx/send-as"><img src="https://agentmods.dev/badge/skills/runxhq/runx/send-as/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/send-as"><img src="https://agentmods.dev/badge/skills/runxhq/runx/send-as.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 | $0.00035 | $0.01778 |
| Opus 5 | $0.00017 | $0.00889 |
| Sonnet 5 | $0.00007 | $0.00356 |
| Haiku 4.5 | $0.00003 | $0.00178 |
Grade A, and why
send-as 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.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Send As
Govern a message, campaign, or notification sent on behalf of a principal.
The default send runner performs one delivery through a compatible normalized
connector and closes only after independent provider readback. plan is the
explicit no-effect runner. apply consumes an existing
runx.send_as.plan.v1 packet without planning again, and verify consumes the
provider mutation result without sending again. Provider-specific skills can
compose these phase runners while retaining the same authority model.
What this skill does
send-as binds the principal, provider, channel, recipients or audience,
content digest, consent basis, preflight checks, and approval gate. The caller
selects only a compatible provider and bounded target; it does not author
provider operations, result fields, payload plumbing, or retry keys. Runx
derives a canonical message.send request from the approved plan, binds its
idempotency key to a native digest, applies it under one approval, and verifies
the stable identity with message.read. It refuses to treat a draft, preview,
mutation acknowledgement, or test message as live delivery. A live send is
final only after provider readback and the Runx receipt seal.
Use plan when only an authorization packet is wanted. A sealed plan receipt
means only that the plan was sealed. A completed default result emits
runx.send_as.result.v1; its sent status is unavailable unless mutation and
readback both succeed.
When to use this skill
- An agent needs to send or schedule one bounded message on behalf of a user, team, brand, account, or service through a compatible connector.
- An operator explicitly wants a plan and selects
plan. - A provider-specific skill needs a shared authority model before it can call a send API or MCP tool.
- The workflow must prove the intended audience, content, consent basis, and approval decision before delivery.
- A review needs to distinguish draft, test, scheduled, approved, sent, denied, and failed states.
What ships with it
8 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/approval-bypass-is-refused.yaml 2.5 KB
- fixtures/campaign-send-plan-ready.yaml 2.6 KB
- fixtures/composed-apply-reuses-plan.yaml 2.6 KB
- fixtures/default-requires-live-delivery-binding.yaml 2.4 KB
- fixtures/default-sends-and-verifies.yaml 3.5 KB
- fixtures/missing-audience-needs-input.yaml 1.8 KB
- send-as.mjs 6.6 KB runs code
- X.yaml 8.0 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.
- 8d ago First seen · 192 lines · 35 tokens per session scan A c9e832105fd3
send-as is a skill published in the GitHub repository runxhq/runx (87 stars, last pushed 3d ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,778 once invoked, about $0.0002 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-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-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-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.