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 skills add IAPro-Community/Orquestrador-Maestro --skill skill-evolution-apigit clone --depth 1 https://github.com/IAPro-Community/Orquestrador-MaestroWrote 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/iapro-community/orquestrador-maestro/skill-evolution-api)<a href="https://agentmods.dev/skills/iapro-community/orquestrador-maestro/skill-evolution-api"><img src="https://agentmods.dev/badge/skills/iapro-community/orquestrador-maestro/skill-evolution-api.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.00778 |
| Opus 5 | $0.00026 | $0.00389 |
| Sonnet 5 | $0.00010 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
skill-evolution-api 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 8d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evolution API
Use this skill when integrating WhatsApp through Evolution API. Treat every message as sensitive customer communication.
Core Workflow
- Confirm the tenant, WhatsApp account owner, business purpose, user consent model, and allowed message categories.
- Keep Evolution API keys, webhook secrets, and instance credentials server-side only.
- Model each instance as tenant-owned state with lifecycle, QR pairing state, webhook status, heartbeat, and disconnect reason.
- Queue outbound sends. Apply per-instance, per-tenant, and per-contact rate limits before enqueueing.
- Assign every outbound request a stable idempotency key based on tenant, instance, recipient, template or body hash, and campaign or workflow ID.
- Treat webhooks as at-least-once delivery. Verify signature when available, dedupe by provider message ID, and make handlers idempotent.
- Persist delivery, read, inbound, disconnect, reconnect, and pairing events as append-only state transitions.
- Redact message bodies in logs unless a support or audit policy explicitly requires short-lived encrypted retention.
- Surface recoverable admin states: QR expired, disconnected, webhook failing, send queued, send failed, rate limited, and consent missing.
Current API Boundary
- Target Evolution API v2+ and use the instance's documented base URL plus the
apikeyheader. - Common v2 routes include
POST /instance/createandPOST /message/sendText/{instanceName}; verify the exact route in the deployed instance's OpenAPI/docs before coding because route shapes can differ between v1 and v2. - Starting with Evolution API v2.4.0, self-hosted instances require activation/licensing before business endpoints serve traffic. Add license status/activation to deployment readiness checks and surface
503activation failures distinctly from WhatsApp failures.
Consent and Compliance
- Require explicit opt-in before sending non-transactional messages.
- Store consent source, timestamp, contact identity, tenant, scope, and revocation timestamp.
- Stop queued campaign or automation messages immediately when consent is revoked.
- Keep templates, campaign labels, and operator identity attached to sends for audit.
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.
- 8d ago First seen · 63 lines · 52 tokens per session scan A 605e3de83945
skill-evolution-api is a skill published in the GitHub repository IAPro-Community/Orquestrador-Maestro (41 stars, last pushed 3d ago), licensed Apache-2.0. It adds 52 tokens to every session and 778 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 2026-08-30.
Other skills, from other repositories
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
composio
Build AI agents and apps with Composio - access 200+ external tools with Tool Router or direct execution.
access-exchange-2010-ews-functions
Exchange 2010 EWS integration for emails, calendar, contacts, and tasks.
fortify
Use when the workflow lacks error handling, has been failing in production, or needs retry logic, fallback strategies, and circuit breakers.
lwip-integration
Use when integrating, porting, configuring, or debugging lwIP TCP/IP stack, netif drivers, memory pools, sysarch, DHCP, TCP, UDP, or embedded networking issues.
annie-universal-api-orchestrator
Use AGNT's stored OAuth tokens and API keys for a third-party API only when no suitable authenticated AGNT tool exists or a working tool lacks the required API capability. Existing provider tools are always the first choice.