Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Malaccamaxgit/whatsapp-mcp-dockernpx agentmods add skills/malaccamaxgit/whatsapp-mcp-docker/cleanupWrote 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/malaccamaxgit/whatsapp-mcp-docker/cleanup)<a href="https://agentmods.dev/skills/malaccamaxgit/whatsapp-mcp-docker/cleanup"><img src="https://agentmods.dev/badge/skills/malaccamaxgit/whatsapp-mcp-docker/cleanup/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/malaccamaxgit/whatsapp-mcp-docker/cleanup"><img src="https://agentmods.dev/badge/skills/malaccamaxgit/whatsapp-mcp-docker/cleanup.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 | $0.00068 | $0.00836 |
| Opus 5.5 | $0.00027 | $0.00334 |
| Sonnet 5.5 | $0.00014 | $0.00167 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
cleanup 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 10d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WhatsApp MCP Docker: Full Cleanup
Gather the context first
Run these two commands. Record the output. They give the real profile and catalog names on this machine.
docker mcp profile ls
docker mcp catalog ls
- The profile name comes from
docker mcp profile ls. Use the profile that hosts opencode. The default iscommon_core. - The catalog name comes from
docker mcp catalog ls. Use the entry that is notmcp/docker-mcp-catalog:latest. That entry is Docker's official catalog. Do not remove it.
Warn the user first
Before any step, tell the user:
MCP tools stop responding during cleanup. After the cleanup, restart the opencode service. Cleanup also deletes all WhatsApp session, message, and audit data in the named volumes. You must authenticate again.
Then ask for confirmation.
Cleanup steps
Run the steps in this exact order.
Step 1: remove the server from the MCP profile
docker mcp profile server remove <PROFILE> whatsapp-mcp-docker
Ignore an error if whatsapp-mcp-docker is not registered.
Step 2: remove the encryption secret
docker mcp secret rm whatsapp-mcp-docker.data_encryption_key
docker mcp secret ls
Ignore an error if the secret does not exist.
Step 3: stop containers and remove the named volumes
Run from the project root.
docker compose down -v --remove-orphans
This step removes the whatsapp-mcp-docker container, the tester-container
container, and the whatsapp-sessions and whatsapp-audit volumes.
Step 4: remove the Docker image
docker rmi malaccamax/whatsapp-mcp-docker:latest
Ignore a No such image error.
Step 5: prune the dangling build-cache layers
The multi-stage Dockerfile creates intermediate builder and test stage
layers. compose down does not remove them.
docker image prune -f
Step 6: remove the custom MCP catalog
docker mcp catalog remove <CATALOG>:latest
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.
- 10d ago First seen · 130 lines · 68 tokens per session scan A 97eb0b8ae824
cleanup is a skill published in the GitHub repository Malaccamaxgit/whatsapp-mcp-docker (1 stars, last pushed 10d ago), licensed Apache-2.0. It adds 68 tokens to every session and 836 once invoked, about $0.0003 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 2026-10-06.
Other skills, from other repositories
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.
managing-astro-local-env
Manage local Airflow environment with Astro CLI (Docker and standalone modes). Use when the user wants to start, stop, or restart Airflow, view logs, query the Airflow API, troubleshoot, or fix environment issues. For project setup, see setting-up-astro-project.
polar-local-environment
This skill should be used when setting up or managing Polar local development environment with Docker.