Borrowing it
Nothing to install: this file belongs to HalemoGPA/whatsapp-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/HalemoGPA/whatsapp-mcp-server/main/.claude/skills/add-tool/SKILL.mdgit clone --depth 1 https://github.com/HalemoGPA/whatsapp-mcp-serverWrote 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/halemogpa/whatsapp-mcp-server/add-tool)<a href="https://agentmods.dev/skills/halemogpa/whatsapp-mcp-server/add-tool"><img src="https://agentmods.dev/badge/skills/halemogpa/whatsapp-mcp-server/add-tool/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/halemogpa/whatsapp-mcp-server/add-tool"><img src="https://agentmods.dev/badge/skills/halemogpa/whatsapp-mcp-server/add-tool.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 | $0.00059 | $0.00940 |
| Opus 5 | $0.00030 | $0.00470 |
| Sonnet 5 | $0.00012 | $0.00188 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
add-tool 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding an MCP tool
Five steps. Skipping step 3 or 4 produces a tool that exists but that the model can never find, which is the same as not shipping it.
1. Write the tool
Tools live in whatsapp-mcp-server/tools.py (general) or scheduling.py
(queue, drafts, notes). Register with @mcp.tool(annotations=...) using one of
the five constants defined at the top of tools.py:
| Constant | For |
|---|---|
READ_LOCAL |
Reads the local store. No network, no side effect. |
READ_BRIDGE |
Reads via the bridge (touches the network), no side effect. |
SEND |
Sends a message or file, non-idempotent. |
MUTATE |
Changes state, recoverable (react, mark read, edit). |
DESTRUCTIVE |
Irreversible: delete, revoke, leave, block. |
A DESTRUCTIVE tool takes confirm: bool = False and calls _require_confirm
before doing anything:
@mcp.tool(annotations=DESTRUCTIVE)
def delete_thing(thing_id: str, confirm: bool = False) -> dict:
"""One-line summary the model reads.
Args:
thing_id: ...
confirm: Must be True. The user, not the LLM, has to have agreed.
"""
if (denied := _require_confirm(confirm)) is not None:
return denied
...
The annotation is only a hint to the client. The confirm kwarg is the actual
enforcement, and it exists because older MCP clients do not support elicitation.
Clamp every caller-supplied bound. The existing tools use limit <= 100,
context windows <= 20, message body <= 65536 bytes. Match them.
2. Decide whether it belongs in the core set
_CORE_TOOLS in server.py is the 29-tool hot core served directly in the
default minimal toolset. Every entry there is paid for on every request to the
model, whether or not WhatsApp is touched.
The bar: would a typical session use this in the first three calls? If not, leave
it out. It stays fully reachable through find_tool / call_tool. Most new
tools should not be in the core.
3. Make it findable
If the tool's name and description do not share vocabulary with how a person
would ask for it, find_tool cannot rank it. schedule_message never lexically
matches "send this tomorrow morning".
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 · 105 lines · 59 tokens per session scan A 4911f2c47b8a
add-tool is a skill published in the GitHub repository HalemoGPA/whatsapp-mcp-server (5 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 940 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
swag
This skill should be used when the user says "add proxy config", "create reverse proxy", "SWAG config", "nginx proxy", "expose service", "proxy configuration", "subdomain config", "subfolder config", "configure SWAG", "list proxy configs", "view proxy config", "edit proxy config", "remove proxy config", "check proxy…
cor-auth
Authentication cheat sheet for the COR MCP Server — covers both auth modes (email/password and client credentials) step by step, token refresh mechanism, and common auth errors.
scrape-batch
Extract many known URLs in one polite, rate-limited pass. Use when the user hands over a list of links, a set of search hits to read in full, or asks to "scrape these pages" / "pull the content from all of them". Drives extract(action="batch"), which fans out with per-domain rate limiting and returns partial results…
knowledge-audit
Review and clean up stored memories — find duplicates, contradictions, stale entries, and consolidate.
memory-commit
Use when the user explicitly says "remember this", "save this", "ghi nho", "luu lai", "save for next time", or otherwise asks to persist the immediately preceding context. Captures with the appropriate contexttype (decision, preference, fact, skill, task, conversation) so future sessions can retrieve it accurately.
recall-context
Use at session start, before significant decisions, or when a new task references a known project to recall mnemo memories matching the current working directory, recently edited files, or topic keywords. Helps maintain continuity across sessions and avoid redoing past research.