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 gokapso/agent-skills --skill integrate-whatsappgit clone --depth 1 https://github.com/gokapso/agent-skillsWrote 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/gokapso/agent-skills/integrate-whatsapp)<a href="https://agentmods.dev/skills/gokapso/agent-skills/integrate-whatsapp"><img src="https://agentmods.dev/badge/skills/gokapso/agent-skills/integrate-whatsapp/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/gokapso/agent-skills/integrate-whatsapp"><img src="https://agentmods.dev/badge/skills/gokapso/agent-skills/integrate-whatsapp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk 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 | $0.00062 | $0.04625 |
| Opus 5.5 | $0.00025 | $0.01850 |
| Sonnet 5.5 | $0.00012 | $0.00925 |
| Haiku 4.5 | $0.00006 | $0.00462 |
Grade A, and why
integrate-whatsapp 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 21d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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.
- assets/dynamic-flow.json 2.5 KB
- assets/sample-flow.json 690 B
- assets/send-interactive-buttons.json 382 B
- assets/send-interactive-catalog-message.json 329 B
- assets/send-interactive-cta-url.json 349 B
- assets/send-interactive-list.json 541 B
- assets/send-interactive-location-request.json 248 B
- assets/send-template-order-status-update.json 843 B
- assets/template-authentication-otp.json 354 B
- assets/template-marketing-media-header.json 513 B
- assets/template-utility-named.json 1.0 KB
- assets/template-utility-order-status-update.json 1.1 KB
- assets/webhooks-example.json 300 B
- package.json 139 B
- references/detecting-whatsapp-connection.md 8.1 KB
- references/getting-started.md 4.3 KB
- references/platform-api-reference.md 4.8 KB
- references/setup-links.md 6.0 KB
- references/templates-reference.md 5.9 KB
- references/webhooks-event-types.md 16 KB
- references/webhooks-overview.md 1.4 KB
- references/webhooks-reference.md 3.3 KB
- references/whatsapp-api-reference.md 13 KB
- references/whatsapp-cloud-api-js.md 3.3 KB
- references/whatsapp-flows-spec.md 60 KB
- scripts/create-flow.js 922 B runs code
- scripts/create-function.js 1021 B runs code
- scripts/create-template.mjs 1.5 KB runs code
- scripts/create.js 2.5 KB runs code
- scripts/delete-flow.js 472 B runs code
- scripts/delete.js 1.9 KB runs code
- scripts/deploy-data-endpoint.js 452 B runs code
- scripts/deploy-function.js 421 B runs code
- scripts/get-data-endpoint.js 444 B runs code
- scripts/get-encryption-status.js 436 B runs code
- scripts/get-flow.js 430 B runs code
- scripts/get-function.js 413 B runs code
- scripts/get.js 1.8 KB runs code
- scripts/lib/args.mjs 1.8 KB runs code
- scripts/lib/cli.js 2.6 KB runs code
- scripts/lib/env.js 1.0 KB runs code
- scripts/lib/env.mjs 1.2 KB runs code
- scripts/lib/http.js 2.8 KB runs code
- scripts/lib/output.js 270 B runs code
- scripts/lib/output.mjs 533 B runs code
- scripts/lib/request.mjs 1.5 KB runs code
- scripts/lib/run.js 768 B runs code
- scripts/lib/security.js 4.4 KB runs code
- scripts/lib/webhooks/args.js 2.6 KB runs code
- scripts/lib/webhooks/kapso-api.js 1.2 KB runs code
- scripts/lib/webhooks/webhook.js 1.6 KB runs code
- scripts/lib/whatsapp-flow.js 1.0 KB runs code
- scripts/list-connected-numbers.mjs 1.4 KB runs code
- scripts/list-flow-responses.js 577 B runs code
- scripts/list-flows.js 909 B runs code
- scripts/list-function-invocations.js 892 B runs code
- scripts/list-function-logs.js 535 B runs code
- scripts/list-platform-phone-numbers.mjs 3.8 KB runs code
- scripts/list-templates.mjs 2.0 KB runs code
- scripts/list.js 2.0 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.
- 21d ago Changed · +1 lines 25d33f0098b5
- 27d ago Changed · +9 lines 9c8d296e8d53
- 2mo ago First seen · 407 lines · 62 tokens per session scan A f8095d672b71
integrate-whatsapp is a skill published in the GitHub repository gokapso/agent-skills (193 stars, last pushed 20d ago), with no licence file. It adds 62 tokens to every session and 4,625 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 2026-08-30.
Other skills, from other repositories
build-mcp-server
This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development — it interrogates…
data-manager-api-setup
Guides developers through client library installation and authentication setup steps for the Data Manager API. Use this skill when a user is getting started with the Data Manager API and needs to setup their local environment, install the client library, or setup access to the API. Don't use for implementing audience…
vss-manage-video-io-storage
Use to drive vss vios for sensor list, timelines, clips, snapshots, and add/delete of video or stream sources, and the VIOS REST API only for what that CLI does not cover (sensor info/status/settings, storage and recorder status, WebRTC, the RTSP proxy, network scan, device settings, bytes to disk, the NvStreamer…
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
vss-search-archive
Use this skill when a user wants to search archived VSS video that is already registered in a configured deployment — by natural-language, similarity, attribute, object-ID, or lexical tag query. Not for fresh clip Q&A, live captioning, video summarization, deployment, or source ingestion/deletion.
new
Create a new project to start development quickly.