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 webhook-handoffgit 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/webhook-handoff)<a href="https://agentmods.dev/skills/runxhq/runx/webhook-handoff"><img src="https://agentmods.dev/badge/skills/runxhq/runx/webhook-handoff/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/webhook-handoff"><img src="https://agentmods.dev/badge/skills/runxhq/runx/webhook-handoff.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 | $0.00044 | $0.00923 |
| Opus 5.5 | $0.00018 | $0.00369 |
| Sonnet 5.5 | $0.00009 | $0.00185 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
webhook-handoff 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 yesterday.
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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Webhook Handoff
Hand off governed runx work to a workflow platform without turning it into the authority holder.
This skill is the outbound side of a workflow integration. runx owns the
policy decision, execution context, and receipt. The receiving platform owns
its webhook, canvas, branching, fan-out, and downstream notifications.
platform chooses the receiver and the connector that delivers to it: n8n
for an n8n Cloud workflow, zapier for a Zapier Catch Hook.
Runners
preflight: validates and normalizes the handoff context without network.send: validates the context and delivers it to the chosen receiver.
Use preflight for reviews, CI, and local harnesses; it never needs approval.
The send runner first calls native control.prepare_handoff, which validates
the execution identity and produces the canonical delivery envelope. It then
runs handoff.deliver on the chosen connector, which posts that envelope after
exact approval: for n8n to https://<workspace>.app.n8n.cloud/webhook/<slug>,
for Zapier to the Catch Hook. Neither platform offers a way to read a delivery
back, so the receipt records the receiver's answer with finality
acknowledged, not a confirmed readback.
Execution context
execution_context must identify where the handoff came from. Include at least
one of:
callerorcaller_idprincipalorprincipal_idworkflow,workflow_id,workflow_ref, orsource_workflowupstream_execution_idorupstream_run_id
When present, these fields must match the top-level inputs:
platformevent_ididempotency_key(bound toevent_id)handoff_scopehandoff_audience
The receiver gets the normalized delivery object, not an independently
reassembled copy of these fields. That object carries the business payload,
source context, exact handoff scope and audience, and idempotency binding the
receiver must validate before starting its workflow.
Edge cases
- Only n8n Cloud hosts are reachable for n8n. A self-hosted instance needs its own connector that declares its host.
- Anyone who knows the webhook path can post to it, so have the receiving
workflow check
handoff_scopeandhandoff_audiencebefore acting. - Do not put raw provider credentials into
payloadorexecution_context. Pass credential references or let runx hold the provider secret. - If an n8n workflow slug changes, update
handoff_audienceto the matchingn8n:workflow:<slug>value. - The receiver must dedupe by
event_idbefore branching or sending downstream notifications.
What ships with it
9 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/composes-in-graph.yaml 182 B
- fixtures/default-delivers-n8n.yaml 2.7 KB
- fixtures/default-delivers-zapier.yaml 2.8 KB
- fixtures/default-reaches-exact-approval.yaml 858 B
- fixtures/n8n-needs-its-webhook-host.yaml 779 B
- fixtures/support/composed.graph 470 B
- references/catalog.md 184 B
- run.yaml 8.5 KB
- webhook-handoff.mjs 1.9 KB runs code
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.
- yesterday First seen · 86 lines · 44 tokens per session scan A a5d93e7e96ca
webhook-handoff is a skill published in the GitHub repository runxhq/runx (103 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 923 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-16.
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.