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 desplega-ai/agent-swarm --skill kapso-whatsappgit clone --depth 1 https://github.com/desplega-ai/agent-swarmWrote 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/desplega-ai/agent-swarm/kapso-whatsapp)<a href="https://agentmods.dev/skills/desplega-ai/agent-swarm/kapso-whatsapp"><img src="https://agentmods.dev/badge/skills/desplega-ai/agent-swarm/kapso-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/desplega-ai/agent-swarm/kapso-whatsapp"><img src="https://agentmods.dev/badge/skills/desplega-ai/agent-swarm/kapso-whatsapp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 204 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 241 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00156 | $0.05543 |
| Opus 5 | $0.00078 | $0.02772 |
| Sonnet 5 | $0.00031 | $0.01109 |
| Haiku 4.5 | $0.00016 | $0.00554 |
Grade A, and why
kapso-whatsapp scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
The curl recipes below assume `$API_BASE`, `$API_KEY`, and `$PHONE_NUMBER_ID` are set in your shell. `get-config` is an MCP tool, not a shell command — call it as a tool first, then export the values it returns: How it starts
The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kapso WhatsApp
Kapso (https://kapso.ai) is a WhatsApp platform vendor that fronts the Meta Cloud API. A swarm provisions one or more WhatsApp phone numbers and wires each one to either the native inbound handler or a workflow that dispatches a task per inbound message.
When to use MCP tools vs this skill's REST recipes
The integration ships thin MCP-tool wrappers for the common case only:
| Tool | Use for |
|---|---|
send-whatsapp-message |
Free-form text within the 24h session window. |
reply-whatsapp-message |
Same as above but quote-threads to an inbound WAMID. |
register-kapso-number / unregister-kapso-number |
Provisioning a phone number's webhook + KV mapping. |
For ANYTHING else, drop to the REST recipes in this skill — these are the canonical reference, and the MCP tools deliberately do NOT duplicate them:
- Template messages (outside 24h window) → §"Send a template" below.
- Media (image / document / audio / video, including wide-image padding and PTT voice notes) → §"Sending media".
- Reactions (👀 / ✅ / clear) → §"Send a reaction".
- Typing indicator + mark-as-read → §"Mark as read + typing indicator".
- Signature verify (manual) → §"Webhook signature verification".
- Contact resolution → swarm user → §"Resolve a contact to a swarm user".
- Conversation history / message detail / templates list → §"Read conversation context".
If the MCP-tool send returns a 24h-window error (sessionWindowExpired: true), fall through to the template path in §"Send a template" — this is exactly what the tool's structured-error points at.
Setup
Swarm config keys (resolve with get-config key:<NAME> includeSecrets:true — Lead-only for secrets; workers should ask Lead if they need a value injected):
| Key | Value |
|---|---|
KAPSO_API_BASE_URL |
https://api.kapso.ai (host only, no /platform/v1) |
KAPSO_API_KEY |
API key (X-API-Key header) |
KAPSO_PHONE_NUMBER_ID |
The swarm's provisioned number's Meta phone-number ID |
KAPSO_WEBHOOK_HMAC_SECRET |
Shared HMAC secret. Kapso signs every webhook request with X-Webhook-Signature: <hex> |
What ships with it
2 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.
- 12d ago First seen · 384 lines · 156 tokens per session scan A 609e7553becc
kapso-whatsapp is a skill published in the GitHub repository desplega-ai/agent-swarm (761 stars, last pushed yesterday), licensed MIT. It adds 156 tokens to every session and 5,543 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
api-testing
Comprehensive API testing, validation, and test suite generation.
ppt-generation
Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Creates visually rich slides by generating images for each slide and composing them into a PowerPoint file.
newsletter-generation
Use this skill when the user requests to generate, create, write, or draft a newsletter, email digest, weekly roundup, industry briefing, or curated content summary. Supports topic-based research, content curation from multiple sources, and professional formatting for email or web distribution. Trigger on requests…
data-analysis
Use this skill when the user uploads Excel (.xlsx/.xls) or CSV files and wants to perform data analysis, generate statistics, create summaries, pivot tables, SQL queries, or any form of structured data exploration. Supports multi-sheet Excel workbooks, aggregation, filtering, joins, and exporting results to…
image-generation
Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.