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 agentmods add skills/felipefontoura/bento/evolution-apinpx skills add felipefontoura/bento --skill evolution-apigit clone --depth 1 https://github.com/felipefontoura/bentoWhat 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 | $0.00181 | $0.01262 |
| Opus 5 | $0.00090 | $0.00631 |
| Sonnet 5 | $0.00036 | $0.00252 |
| Haiku 4.5 | $0.00018 | $0.00126 |
Grade A, and why
evolution-api scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
(`curl --max-time 180`). How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You operate the Evolution API on a bento VPS that is already deployed. This skill carries the bento-specific wiring and the operational traps — for the exact endpoint paths and request bodies, go to the official docs (linked at the bottom); they are the source of truth and they move faster than this file. Your job is to know how to approach it, not to memorize the reference.
Mutate via the HTTP API, not the DB or container disk. Read-only inspection (logs, env) to recover a lost key is fine.
When to invoke
- "connect my WhatsApp / get the QR / scan the code"
- "send a WhatsApp message (text or media)"
- "set up / check a webhook for incoming messages"
- "check connection state / list instances / disconnect / delete"
For getting Evolution running use /bento:deploy.
Discover the instance — don't hardcode
# The stack name has a dash — confirm the exact state key first
ssh "$user@$host" "jq '.envs|keys' \$HOME/.config/bento/state.json"
ssh "$user@$host" "jq -r '.envs.\"evolution-api\".EVOLUTION_HOST' \$HOME/.config/bento/state.json" # base URL host
ssh "$user@$host" "jq -r '.envs.\"evolution-api\".EVOLUTION_API_KEY' \$HOME/.config/bento/state.json" # global key (never echo)
Base URL = https://<EVOLUTION_HOST>. Swarm task: evolution-api_evolution.1.*
(stack evolution-api, service evolution — confirm with docker ps).
Auth — the part that isn't obvious from the docs
Evolution uses a flat apikey: <key> header — not Authorization: Bearer.
There are two keys, and using the wrong one is the #1 source of 401s:
| Key | Scope | Source |
|---|---|---|
| Global | lifecycle: create / list / delete / logout instances | EVOLUTION_API_KEY (bento state) |
| Instance | messaging + per-instance config (send, webhooks, state) | hash.apikey in the POST /instance/create response; re-readable via fetchInstances |
Rule: global key for instance lifecycle, instance key for everything you do to an instance.
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.
- 2d ago First seen · 89 lines · 181 tokens per session scan A 64bb170b35e4
evolution-api is a skill published in the GitHub repository felipefontoura/bento (20 stars, last pushed 1mo ago), licensed MIT. It adds 181 tokens to every session and 1,262 once invoked, about $0.0009 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
superplane-changelog
When generating a SuperPlane changelog from merged commits. Use for "what's new" summaries with new integrations, new components/triggers, improvements, security updates, and bug fixes. Output is user-focused markdown in tmp/.
review-agents-md
Audit Dograh AGENTS.md files for drift against the live repo and for bad scope boundaries between parent and child docs. Use when the user asks to review existing AGENTS files, identify stale guidance, decide whether a subtree needs its own AGENTS.md, or update the AGENTS.md hierarchy under the repo root, api/, or ui/.
simplified-technical-english
Write user-facing and reviewer-facing technical text in ASD-STE100 Simplified Technical English style. Use when drafting PR descriptions, commit message bodies, UI copy, docs, error messages, procedures, onboarding text, or any product wording that must stay clear for non-native readers.
pandic-office
Convert Markdown to PDF (or DOCX/EPUB/HTML) using the pandoc CLI. Use when asked to produce a PDF report, brief, summary, or any document where the input is Markdown and the output should be a polished, paginated file.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
experiment-tracking-swanlab
Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.