simplicio-agent

Legacy compatibility alias for `/simplicio-loop`. Use only when an older install, adapter, or saved prompt still invokes `/simplicio-tasks`; immediately route the run through `.claude/skills/simplicio-loop/SKILL.md`, which now owns the public core + loop protocol.

Operate and troubleshoot local Hermes/Simplicio gateway services safely, including config edits, launchd/service restarts, and live verification with logs.

Transforma a memória do Simplicio (memory_items + embeddings all-MiniLM) em um knowledge graph consultável — nós + arestas, comunidades, god nodes, path/explain/query. Port do conceito Graphify (Graphify-Labs) reusando a infra já existente (neural-recall, vec0).

Legacy compatibility alias for `/simplicio-loop`. Use only when an older install, adapter, or saved prompt still invokes `/simplicio-tasks`; immediately route the run through `.claude/skills/simplicio-loop/SKILL.md`, which now owns the public core + loop protocol.

Learned skill -- when the task mentions "not", run this proven sequence (5 successful runs, confidence 1.00).

Evolutionary optimize-by-metric loop — mutate a target, evaluate against fixed criteria, KEEP if the score improves (commit) or REVERT if it doesn't (git checkout), repeat, plateau-break after N stagnated runs. Adapts Karpathy's `autoresearch` pattern (and the ECC `autoresearch-agent`) with mandatory yool guardrails (§11 caps), git-isolated branch discipline, an anti-Goodhart eval order (correctness gate FIRST, score SECOND, labeled tokenizer), a local-first mutation ladder, and a `simplicio.savings-event/v1` receipt per run. Use when the user says "optimize this by <metric>", "autoresearch loop", "evolutionary optimize", "mutate/eval/keep-revert", or asks to shrink tokens/latency/bundle size/improve pass-rate against a fixed, measurable eval. Worker: `scripts/autoresearch.py`.

Cut output and memory tokens without losing meaning — terse prose levels (caveman-style) that preserve code/paths/URLs byte-for-byte, plus a one-time memory/doc compaction pass that pays back every future turn. Use when replies or worker reports are verbose, when standing context (CLAUDE.md/AGENTS.md/notes) is bloated, or when simplicio-tasks needs its output-side + input-side token discipline. Compression NEVER touches code, identifiers, or a safety confirmation.

Persist what a run taught you so the next run is cheaper and more correct — mine high-signal lessons from the trajectory, dedup them, and write them back to AGENTS.md / memory so they're applied not re-derived. Use after a run or at session end, when the user says "remember this", "do a retrospective", "learn from this run", or when simplicio-tasks closes its self-audit. Keeps memory lean: durable, reusable bullets only — no transcripts, no one-offs.

Unified public entrypoint for Simplicio's body-of-work orchestration: core + loop in one command. Use when the user types /simplicio-loop, says "ralph loop", "keep iterating until done", "finish all open issues", or asks to drain a queue of work autonomously. Runtime-agnostic: binds a real stop-hook where the host supports hooks (Claude, Cursor); otherwise self-paces via the host scheduler. The older /simplicio-tasks surface is a legacy alias; never escape the loop with a false promise.

Terminal-first execution — answer facts with the shell, never with the LLM. Use whenever a step needs a fact about the filesystem, git, processes, or system resources, or runs a build/test/lint/diff whose output would flood context. Substitutes deterministic shell/CLI calls for native LLM operations and clamps their output 60–90% (rtk-style) with a failure-safe tee cache, signatures-only reads, and an optional auto-rewrite hook. This is the token-economy spine of simplicio-tasks, usable standalone.

Deep, adversarial branch review — parallel subagents on separate rubrics (security/correctness, code-quality, and does-it-reproduce), spawned in one message, then deduped into one verdict. Runs for EVERY item, no TRIVIAL/SMALL shortcut — it is 3 of the 6 roles in simplicio-tasks' minimum-agent floor. Use before merging any work, when the user says "review this branch/PR hard", "thermo-nuclear review", "is this safe to merge", or when simplicio-tasks needs the Step 4c adversarial verify gate. Scopes strictly to the diff; refutes rather than rubber-stamps.

Himalaya CLI: IMAP/SMTP email from terminal.

Airtable REST API via curl. Records CRUD, filters, upserts.

Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.

Notion API + ntn CLI: pages, databases, markdown, Workers.

Extract text from PDFs/scans (pymupdf, marker-pdf).

Install and select animated petdex mascots for Simplicio Agent.

Operate the Teams meeting summary pipeline via Simplicio Agent CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.

Evolve the Simplicio Runtime by porting external patterns into runtime modules with deterministic edits, focused tests, and evidence. HARD MANDATE (Wesley 2026-07-08) — BOTH bots (AlfradHD ~/.hermes, Simplicio ~/.simplicio_agent) drive execution through Simplicio Runtime via MCP/CLI, and verified evolution is merged straight into `main` of both repos. Encodes the git-to-main pitfalls (worktree trap, origin/main advanced, stash preservation, MCP quirks) and `doctor --json` gap detection.

Plan, set up, and monitor a multi-agent video production pipeline backed by Hermes Kanban. Use when the user wants to make ANY video — narrative film, product/marketing, music video, explainer, ASCII/terminal art, abstract/generative loop, comic, 3D, real-time/installation — and the work warrants decomposition into specialized profiles (writer, designer, animator, renderer, voice, editor, etc.) coordinated through a kanban board. Performs adaptive discovery to scope the brief, designs an appropriate team for the requested style, generates the setup script that creates Hermes profiles + initial kanban task, then helps monitor execution and intervene when tasks stall or fail. Routes scenes to whichever Hermes rendering / audio / design skill fits each beat (`ascii-video`, `manim-video`, `p5js`, `comfyui`, `touchdesigner-mcp`, `blender-mcp`, `pixel-art`, `baoyu-comic`, `claude-design`, `excalidraw`, `songsee`, `heartmula`, …) plus external APIs for TTS, image-gen, and image-to-video as needed.

Migrate a user's OpenClaw customization footprint into Hermes Agent. Imports Hermes-compatible memories, SOUL.md, command allowlists, user skills, and selected workspace assets from ~/.openclaw, then reports exactly what could not be migrated and why.

Join a Google Meet call, transcribe live captions, optionally speak in realtime, and do the followup work afterwards. Use when the user asks the agent to sit in on a meeting, take notes, summarize, respond in-call, or action items from it.

Configure, extend, or contribute to Hermes Agent.

YouTube transcripts to summaries, threads, blogs.

Port dos padrões Asolaria (JesseBrown1980) para o Simplicio Runtime como primitivas determinísticas testáveis — N-Nest cosign/corrective gate, HRM two-level planner, BEHCS-256 supervisor federado.

Search/download GIFs from Tenor via curl + jq.

Hyperliquid market data, account history, trade review.

Query Solana blockchain data with USD pricing — wallet balances, token portfolios with values, transaction details, NFTs, whale detection, and live network stats. Uses Solana RPC + CoinGecko. No API key required.

Poll RSS, JSON APIs, and GitHub with watermark dedup.

Public-records OSINT investigation framework — SEC EDGAR filings, USAspending contracts, Senate lobbying, OFAC sanctions, ICIJ offshore leaks, NYC property records (ACRIS), OpenCorporates registries, CourtListener court records, Wayback Machine archives, Wikipedia + Wikidata, GDELT news monitoring. Entity resolution across sources, cross-link analysis, timing correlation, evidence chains. Python stdlib only.

Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.

Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.

Search arXiv papers by keyword, author, category, or ID.

Query Polymarket: markets, prices, orderbooks, history.

Create and configure Discord servers, categories, channels, and messages via Playwright browser automation. Covers login flow, DOM interaction patterns specific to Discord's React UI, and known pitfalls.

Direct browser control via CDP. Use when the user wants to automate, scrape, test, or interact with web pages. Connects to the user's already-running Chrome.

Close Autopilot v5 issues and create new feature issues

Comprehensive security and correctness audit of a branch's changes. Use for thermo nuclear, thermonuclear, or deep review requests, or branch/PR diff audits focused on bugs, breaking changes, security issues, devex regressions, and feature-gate leaks.

Launch both thermo-nuclear review subagents in parallel, then synthesize their findings. Use for thermos, double thermo review, or combined bug/security and code-quality branch audits.

Use when evolving a terminal/chat interface (TUI) into a continuous, proactive, multi-agent swarm with Hermes-like capabilities. Covers persistent looping, agents delegate, rich tool calling, vector memory, proactivity, provider/model selection, vision, generation, web search, and rich panel simulation. This skill encodes the full workflow for making a runtime like Simplicio have full Hermes Agent parity.