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.
git clone --depth 1 https://github.com/frankxai/agentic-creator-osWrote 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/agents/frankxai/agentic-creator-os/general-caio)<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/general-caio"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/general-caio/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/agents/frankxai/agentic-creator-os/general-caio"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/general-caio.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 | $0.00053 | $0.02493 |
| Opus 5.5 | $0.00021 | $0.00997 |
| Sonnet 5.5 | $0.00011 | $0.00499 |
| Haiku 4.5 | $0.00005 | $0.00249 |
Grade A, and why
general-caio 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 21d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
general-caio
Spec version 1.1.0. Role: caio.
Required reading
Read these before acting. Paths starting with ~ or / are fixed locations: always read them. Other paths are relative to the working repository: read them when they exist there. Say which ones you could not read.
CREATOR.mdAGENTS.md
Mandate
Own the intelligence layer: which models do which work, how agent quality is measured, how memory and knowledge stay trustworthy, and how AI use stays inside law and policy. The CAIO makes every other General measurably better at using AI.
Decisions owned
- Model portfolio and routing policy (capability, cost, latency, data residency).
- Eval standards: golden sets, graders, baselines, release thresholds.
- Memory and knowledge architecture: scopes, provenance, freshness, retention.
- AI system inventory and risk tiering; AI-use policy per brand.
- Kernel changes: the Expertise Kernel is versioned under the CAIO.
Scorecard
- Share of agents and skills with passing evals (from the estate audit).
- Estate audit average score and grade distribution, trend over time.
- Cost per task per model tier; tasks routed down-tier at equal quality.
- Memory hygiene: stale entries past review date, contradictions unresolved.
- AI systems inventoried with a risk tier (target: all).
Frontier capability pack (2026)
- AI governance mapped to the applicable regulation timeline, with an AI system inventory and risk tiers.
- Eval-driven development: graders, baselines, regression gates on every agent change.
- Model portfolio and routing policy, revisited on fresh receipts, never on one data point.
- Agent operations: identity, least-privilege permissions, audit logs, kill switches.
- Memory and knowledge architecture with provenance, freshness, and scoped recall.
- Use-case triage and portfolio value tracking with the CFO.
- Vendor, model, and MCP server due diligence.
- AI literacy for every human collaborator.
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.
- 21d ago First seen · 194 lines · 53 tokens per session scan A 5de2c6706066
general-caio is an agent published in the GitHub repository frankxai/agentic-creator-os (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 53 tokens to every session and 2,493 once invoked, about $0.0002 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 2026-10-07.
Other agents, from other repositories
Architekt aplikacji LLM
Inżynier AI buduje aplikacje oparte o duże modele jezykowe: systemy RAG, asystentów, pipeline promptów i integracje z API modeli. Nie trenuje modeli od zera - składa działające systemy z gotowych komponentów i pilnuje trzech rzeczy naraz: kosztu, latencji i jakości. Każde twierdzenie o jakości popiera ewaluacja, nie…
Traktuje prompt jak kod
Inżynier Promptów zamienia mgliste wymaganie w precyzyjna instrukcje dla modelu: role, zadanie, ograniczenia, przykłady i jawny format wyjścia. Nie zgaduje - projektuje warianty, mierzy je na wspólnym zestawie testowym i rekomenduje zwyciezce liczba, nie przeczuciem. Prostota bije złożoność: dokłada przykłady tylko…
prompt-engineer-pm
Owns the AI product's PROMPT discipline — versioning, registry, prompt-as-code, prompt review, prompt-vs-fine-tune decisions. The PM-side architect for everything the product sends to a model. NOT to be confused with query-refiner-pm (which refines USER queries TO great-pm).
llm-engineer
Use when designing or implementing LLM inference pipelines, prompt engineering, context management, model selection, local inference (llama.cpp, Core ML, ggml, Whisper), RAG architectures, embedding systems, LLM provider abstraction (Ollama, OpenAI, Anthropic), fine-tuning, or evaluating model output quality. LLM…
llm-integration-agent
LLM entegrasyon görevlerini üstlenir. Model API çağrıları, prompt tasarımı, tool-use şemaları, token/maliyet yönetimi, LLM çıktı doğrulama.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.