Borrowing it
Nothing to install: this file belongs to mblode/eve-whatsapp-group-agent. 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/mblode/eve-whatsapp-group-agent/main/AGENTS.mdgit clone --depth 1 https://github.com/mblode/eve-whatsapp-group-agentWrote 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/instructions/mblode/eve-whatsapp-group-agent/agents-md)<a href="https://agentmods.dev/instructions/mblode/eve-whatsapp-group-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/mblode/eve-whatsapp-group-agent/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.
<a href="https://agentmods.dev/instructions/mblode/eve-whatsapp-group-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/mblode/eve-whatsapp-group-agent/agents-md.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 | $0.01168 | $0.01168 |
| Opus 5.5 | $0.00467 | $0.00467 |
| Sonnet 5.5 | $0.00234 | $0.00234 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
eve-whatsapp-group-agent 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 2mo 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
eve-whatsapp-group-agent
An AI agent that lives in a WhatsApp group and replies when @mentioned, built on the eve framework. Two deployables:
agent/— the eve agent (TypeScript), deploys to Vercel. Tools, channels and instructions are files underagent/.bridge/— a Baileys WhatsApp ↔ agent bridge (TypeScript run via tsx, Node >=20), deploys to Railway. A separate npm package with its own tsconfig and tests; not covered by the root tsgo or vitest.
Before writing agent code, read the relevant guide in node_modules/eve/docs/ (channels, tools, schedules, evals). New here? Start with docs/build-your-own-whatsapp-agent.md.
Install both packages first: npm install (root, Node 24) and cd bridge && npm install (bridge, Node >=20).
npm run dev— eve dev TUI (hot-reloads the agent)npm test— vitest unit tests (agent/**/*.test.ts,tests/**/*.test.ts)npm run typecheck— tsgo (agent, evals, scripts, tests)npm run check— lint + format (ultracite); pre-commit auto-runsultracite fixnpm run test:evals— eve eval (LLM-judged); needs AI Gateway creds, skips without themnpm run build— eve build (Vercel output)cd bridge && npm test— bridge unit tests (tsx --test);cd bridge && npm run typecheck— bridge tsc
Run npm test and npm run typecheck before committing.
Make it yours
- Persona:
agent/lib/base-instructions.tsis the neutral starter prompt. Change the bot's name (matchBOT_NAMEon the bridge), the community, the voice, and the "who's who".agent/lib/easter-eggs.tsis empty by default. - Roster:
bridge/members.tsships two fake example members. Replace them with your own (keyed by E.164 phone). It's the single source of truth for both the bridge's DM allowlist and the agent's who-is/roster tools. - Chat archive:
agent/lib/data/chat-data.tsships empty. Populate it from your own group export withscripts/reingest-archive.ts(seescripts/README.md).search-chatalso merges the bridge's live tail at query time, so the bot works on recent messages even before you bake an archive.
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.
- 2mo ago First seen · 44 lines · 1,168 tokens per session scan A e71b166558e2
eve-whatsapp-group-agent AGENTS.md is an instructions file published in the GitHub repository mblode/eve-whatsapp-group-agent (4 stars, last pushed 22d ago), licensed MIT. It adds 1,168 tokens to every session, about $0.0047 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.
eve-whatsapp-group-agent AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| eve-whatsapp-group-agent AGENTS.mdmblode/eve-whatsapp-group-agent | Instructions file | 4 | 22d ago | MIT | A | 1,168 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |