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 andregusman-raiz/a-gusman-claude --skill ag-referencia-anti-ciclo-preditivogit clone --depth 1 https://github.com/andregusman-raiz/a-gusman-claudeWrote 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/andregusman-raiz/a-gusman-claude/ag-referencia-anti-ciclo-preditivo)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-referencia-anti-ciclo-preditivo"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-referencia-anti-ciclo-preditivo/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/skills/andregusman-raiz/a-gusman-claude/ag-referencia-anti-ciclo-preditivo"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-referencia-anti-ciclo-preditivo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00042 | $0.09530 |
| Opus 5.5 | $0.00017 | $0.03812 |
| Sonnet 5.5 | $0.00008 | $0.01906 |
| Haiku 4.5 | $0.00004 | $0.00953 |
Grade A, and why
ag-referencia-anti-ciclo-preditivo 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 1mo 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 — 741 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anti-Ciclo Preditivo — Regras Universais
30 regras derivadas de diagnostico pos-mortem de um sistema preditivo que consumiu 6 meses e 13 iteracoes sem confirmar sinal preditivo. Custo de descobrir cada regra = ~2 semanas de ciclo real. Aplicaveis a qualquer projeto: churn, inadimplencia, fraud, forecasting, scoring, anomaly, recommendation.
Escopo: compoe com ~/Claude/CLAUDE.md (workspace) e CLAUDE.md local do projeto.
Quando carregar: inicio de qualquer projeto preditivo, antes de treinar modelo, antes de declarar "sinal detectado", antes de deploy de pipeline preditivo.
Navegacao
- I — Epistemologia (M1-M10)
- II — Arquitetura (M11-M15)
- III — Decisao (R1-R3)
- IV — Data Coverage (DC1-DC3)
- V — Multi-segmento (S1-S3)
- VI — Particoes/Populacoes (P1-P3)
- VII — Metodologia (M16-M18)
- VIII — Ground-truth (G1-G3)
- IX — Adversariais (A1-A3)
- X — Meta-regra de composicao (tiers + 5 criticas)
- Apendice A — Mapa sintoma → regra
- Apendice B — Enforcement roadmap
- Apendice C — Aplicacao em projetos Raiz
Vocabulario agnostico
| Termo | Significado |
|---|---|
| Sinal preditivo | Lift estatisticamente significativo de um modelo/estrategia sobre baseline trivial |
| Ground-truth observavel | Valor real do target, acessivel apenas apos o instante de decisao T-0 |
| Baseline forte | Modelo simples (regressao linear, heuristica de negocio, regra de ouro) + fonte de referencia externa confiavel |
| Walkforward / OOT | Validacao temporal onde treino usa apenas dados =T |
| Kill-criterion | Criterio pre-registrado de abandono do projeto (threshold + amostra minima + CI) |
| Null test | Teste com labels embaralhadas / assignment aleatorio para calibrar noise floor |
| Noise floor | Magnitude de efeito produzida sob hipotese nula (zero sinal) por artefato matematico |
| Metrica primaria | Metrica que define sucesso do projeto (ROI, F1, recall@K, precision, AUC, Brier, log-loss, etc) |
| Metrica de calibracao | Metrica que mede "quao bem-calibradas sao as probabilidades" (Brier, log-loss, ECE, reliability) |
| Ciclo N | N-esima iteracao de "vou melhorar o sistema"; ciclos tipicos sao 2-4 semanas cada |
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.
- 1mo ago First seen · 741 lines · 42 tokens per session scan A 598d84079fa4
ag-referencia-anti-ciclo-preditivo is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (18 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 9,530 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 2026-09-03.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…