What is whatsapp-mcp-server AGENTS.md?

Release instructions for an Electron desktop application, including how its versions are created, packaged, published, and updated. Electron is a framework for building desktop apps with web technologies.

Use them when running or changing the GitHub Actions release workflow, producing macOS, Linux, or Windows installers, rebuilding an existing release tag, or maintaining automatic updates.

They give coding agents one agreed process for making releases and avoid conflicting automated builds that can break updates.

How panghy/whatsapp-mcp-server configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to panghy/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.

Copy the file

curl -O https://raw.githubusercontent.com/panghy/whatsapp-mcp-server/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/panghy/whatsapp-mcp-server

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/panghy/whatsapp-mcp-server/agents-md/github.svg)](https://agentmods.dev/instructions/panghy/whatsapp-mcp-server/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/panghy/whatsapp-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/panghy/whatsapp-mcp-server/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/panghy/whatsapp-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/panghy/whatsapp-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,739 This file is loaded in full into every session.

When invoked 1,739 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01739	$0.01739
Opus 5.5	$0.00696	$0.00696
Sonnet 5.5	$0.00348	$0.00348
Haiku 4.5	$0.00174	$0.00174

Measured 1mo ago against content hash 13dc4c3fef10, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

whatsapp-mcp-server AGENTS.md 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 1mo 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.

AGENTS.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Release Documentation for AI Agents

Release Architecture

semantic-release for versioning (config: .releaserc.json)
electron-builder for building/packaging (config: package.json → "build" section)
GitHub Actions workflow at .github/workflows/release.yml
Builds for:
- macOS: dmg + zip
- Linux: AppImage
- Windows: nsis + portable
Auto-updater: Uses electron-updater, checks latest-mac.yml / latest-linux.yml / latest.yml on the GitHub release

How Releases Are Triggered

Two trigger methods:

Manual (preferred): Go to GitHub Actions → "Release" workflow → "Run workflow". Optionally provide a tag (e.g. v1.2.3) to rebuild a specific version, or leave empty to let semantic-release auto-determine version.
Rebuild existing tag: Use the workflow_dispatch with a specific tag input (e.g. v1.2.3) to rebuild and re-upload artifacts for an existing release. When a tag is given, the semantic-release job is skipped so the rebuild cannot create a new, asset-less release.

IMPORTANT: Do NOT add push-to-main triggers — this caused race conditions in the past where two parallel runs (push + tag) uploaded conflicting assets with mismatched SHA512 checksums, breaking the auto-updater.

Workflow Jobs

semantic-release — Only runs on branch pushes (workflow_dispatch). Analyzes commits and creates a new GitHub release + tag if warranted. Uses RELEASE_TOKEN secret (PAT) to bypass branch protection.
build — Runs on all 3 OS matrix (macos-latest, ubuntu-latest, windows-latest). Checks out the tagged commit, syncs package.json version, builds with electron-builder, and uploads artifacts to the GitHub release with --publish always.
publish-release — Ensures the release is not a draft after all builds complete.

Commit Conventions

semantic-release uses Angular preset with these release rules (from .releaserc.json):

feat: → minor
fix: → patch
perf: → patch
refactor: → patch
chore: → patch

Read the full file on GitHub · 120 lines

Changes

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.

1mo ago Changed · +6 lines · +120 tokens per session 13dc4c3fef10
1mo ago Changed · +1 lines · +129 tokens per session bcd1cb193f99
2mo ago First seen · 113 lines · 1,490 tokens per session scan A 3de27cba435e

Subscribe to this mod's changes

whatsapp-mcp-server AGENTS.md is an instructions file published in the GitHub repository panghy/whatsapp-mcp-server (6 stars, last pushed 1mo ago), licensed MIT. It adds 1,739 tokens to every session, about $0.0070 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 2026-08-31.

Git and workflow Releases

whatsapp-mcp-server AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
whatsapp-mcp-server AGENTS.mdpanghy/whatsapp-mcp-server	Instructions file	6	1mo ago	MIT	A	1,739	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

whatsapp-mcp-server: Instructions file for Codex