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 zapier-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/zapier-handoff)<a href="https://agentmods.dev/skills/runxhq/runx/zapier-handoff"><img src="https://agentmods.dev/badge/skills/runxhq/runx/zapier-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/zapier-handoff"><img src="https://agentmods.dev/badge/skills/runxhq/runx/zapier-handoff.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 | $0.00039 | $0.00762 |
| Opus 5 | $0.00019 | $0.00381 |
| Sonnet 5 | $0.00008 | $0.00152 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
zapier-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 9d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zapier Handoff
Hand off governed runx work to a Zapier Catch Hook while keeping authority, provider credentials, and receipts in runx.
This skill is for the outbound side of the Zapier integration story. It is not the public Zapier App Directory app; that app should call hosted runx APIs. This skill gives the same execution-context contract to local dogfood and any operator-owned Zap that receives governed effects from runx.
Runners
preflight: validates and normalizes the handoff context without network.send: validates the context, invokes the selected Catch Hook, and reads the invocation back.
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
uses the provider boundary for hook.invoke; that boundary owns the exact
approval, credential custody, idempotency, and provider operation. A separate
provider read verifies the same event and invocation reference. The compatible
binding may be local or hosted; the skill does not assume credential custody.
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 Catch Hook receives the normalized delivery object, not a second
package-authored rendering. It carries the business payload, source context,
exact handoff scope and audience, and idempotency binding the Zap must validate
before any downstream action.
Edge cases
- Public Zapier directory work must use hosted HTTPS runx APIs, not a local Catch Hook template.
- Do not include payment, token-transfer, or settlement actions in public Zapier v1. This local skill can model a hook handoff, but the public app must stay non-payment until review constraints are satisfied.
- Do not put raw provider credentials into
payloadorexecution_context. Pass credential references or let runx hold the provider secret. - Zapier may retry or replay hook deliveries. The Zap must dedupe by
event_idbefore downstream actions. - A missing compatible Zapier binding is an actionable preflight blocker, not permission to fall back to ambient HTTP or an embedded token.
What ships with it
3 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.
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.
- 9d ago First seen · 81 lines · 39 tokens per session scan A fa960978f3a8
zapier-handoff is a skill published in the GitHub repository runxhq/runx (87 stars, last pushed 3d ago), licensed Apache-2.0. It adds 39 tokens to every session and 762 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
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.
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.