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 neurarelay/relay-action-card --skill neura-before-sendgit clone --depth 1 https://github.com/neurarelay/relay-action-cardWrote 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/neurarelay/relay-action-card/neura-before-send)<a href="https://agentmods.dev/skills/neurarelay/relay-action-card/neura-before-send"><img src="https://agentmods.dev/badge/skills/neurarelay/relay-action-card/neura-before-send/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/neurarelay/relay-action-card/neura-before-send"><img src="https://agentmods.dev/badge/skills/neurarelay/relay-action-card/neura-before-send.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00041 | $0.00227 |
| Opus 5 | $0.00020 | $0.00113 |
| Sonnet 5 | $0.00008 | $0.00045 |
| Haiku 4.5 | $0.00004 | $0.00023 |
Grade A, and why
neura-openclaw-before-send 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 12d 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.
What it actually says
Neura Before Send
Use this skill before outbound agent messages are delivered. Create a refs-only Action Card for the proposed send action and route it to Relay for a Decision Receipt before the user or runtime sends anything.
This is an example skill, not an official OpenClaw or ClawHub integration, listing, approval, or partnership.
Check
- recipient or channel ref is present
- user intent ref is present
- draft/message ref is present without raw body content
- policy or communication-review ref is present
- delegated authority covers message sending for this target
- risk category reflects customer, partner, legal, or public communication impact
Output
Return a Decision Receipt-ready Action Card draft, missing refs, and the recommended hold/proceed posture. Do not send the message and do not include raw message bodies, secrets, credentials, private payloads, or token values.
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.
- 12d ago First seen · 24 lines · 41 tokens per session scan A 11620378eae6
neura-openclaw-before-send is a skill published in the GitHub repository neurarelay/relay-action-card (2 stars, last pushed 19d ago), licensed MIT. It adds 41 tokens to every session and 227 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 2026-08-31.
Other skills, from other repositories
loom-integrations
Configure and verify CodexLoom external platform integrations with the loom CLI. Use when inspecting or changing Connections, Agent Addresses, DM access, group/channel Conversation Memberships, trigger and reply policies, allow/block rules, trust domains, or Inbox/Outbox delivery for Feishu/Lark, Slack, Parall, and…
loom-communication
Use for communication between long-lived CodexLoom Agents: discovering domain owners, deciding when to contact another Agent, sending requests or notifications, replying to an agentmessage, checking queued delivery, and closing a request without a reply. Trigger whenever an Agent receives an agentmessage envelope or…
loom-external-messaging
Send and resolve governed external messages through CodexLoom. Use whenever an Agent receives an external Inbox message from Feishu/Lark, Slack, Parall, or another Connector; must reply, explicitly decline, or defer an external Inbox item; needs to publish proactively to an authorized Conversation Membership; sends…
domain-agent-coaching
Coach the design and ongoing reflection of long-lived domain Agents and Agent organizations. Use when defining or revising Identity, Domain, Scope, Organization or Collaboration relationships; deciding whether recurring work should become an Agent, Internal Agent, Skill, or Task; examining overlap, gaps, overloaded…
loom-topics
Coordinate bounded work that spans multiple Turns, days, or CodexLoom Agents through a shared Topic. Use when a workstream needs one Responsible Agent, scoped Participants, a versioned current brief, waiting conditions, evidence links, or recovery after time has passed; when receiving loomtopiccontext; or when…
loom-feishu
Read Feishu/Lark messages, topic replies, and chat history through CodexLoom's managed Connector. Use when a Feishu Inbox or dispatch lacks enough context; a chat, message, topic root, or reply chain must be inspected; current Feishu history is needed before replying; or the user asks what happened in a Feishu topic.…