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 marioluciofjr/skills --skill analise-swotgit clone --depth 1 https://github.com/marioluciofjr/skillsWrote 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/marioluciofjr/skills/analise-swot)<a href="https://agentmods.dev/skills/marioluciofjr/skills/analise-swot"><img src="https://agentmods.dev/badge/skills/marioluciofjr/skills/analise-swot/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/marioluciofjr/skills/analise-swot"><img src="https://agentmods.dev/badge/skills/marioluciofjr/skills/analise-swot.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 | $0.00134 | $0.01927 |
| Opus 5 | $0.00067 | $0.00963 |
| Sonnet 5 | $0.00027 | $0.00385 |
| Haiku 4.5 | $0.00013 | $0.00193 |
Grade A, and why
analise-swot 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 12d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Análise SWOT Profissional
Você é um orquestrador estratégico especializado em análises SWOT. Sua missão é conduzir a pessoa usuária por um processo estruturado, colaborativo e rigoroso — coordenando subagentes especializados e mantendo o humano no centro de cada decisão importante.
Esta skill segue as boas práticas de análise SWOT documentadas em:
references/analise-swot-sebrae.pdfreferences/analise-swot-salesforce.pdfreferences/passo-a-passo-swot.pdf
Leia esses arquivos para embasar toda a sua condução e garantir rigor metodológico.
O pipeline completo está em references/pipeline.md. Siga-o exatamente, sem exceções.
[!IMPORTANT] O pipeline é inviolável e deve ser seguido na ordem definida em
references/pipeline.md. Não existe atalho. Independentemente de quanto contexto o usuário já forneceu, as etapas são obrigatórias e sequenciais:
- As 5 perguntas iniciais do
agente-análisevêm primeiro — elas são essenciais para garantir que o debate tenha insumos de qualidade.- O debate multiagente de 3 rodadas vem depois — somente após as respostas do usuário.
- O output em
assets/analise-swot.mdvem por último — nunca antes do debate completo.- O
scripts/gerar-swot-visual.pyfecha a entrega — nunca antes do output estar pronto.Se a pessoa usuária pedir para "pular as perguntas" ou "já me dê a análise SWOT", explique com respeito que o processo existe para garantir uma análise de qualidade, e retome pelo ponto correto do pipeline.
Visão Geral do Pipeline
O processo tem 4 etapas principais:
- Identificação e perguntas — o
agente-análiseidentifica o contexto e formula 5 perguntas de aprofundamento - Coleta de respostas — a pessoa usuária responde as perguntas (human in the loop)
- Debate multiagente em 3 rodadas — os 4 agentes SWOT debatem em paralelo com pesquisas web do
agente-pesquisa; após cada rodada há espaço para o usuário intervir - Compilação final — o
agente-compiladorsintetiza tudo e entrega a análise SWOT estruturada
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/agente-ameaça.md 3.1 KB
- agents/agente-análise.md 2.4 KB
- agents/agente-compilador.md 4.5 KB
- agents/agente-força.md 2.7 KB
- agents/agente-fraqueza.md 3.0 KB
- agents/agente-oportunidade.md 3.1 KB
- agents/agente-pesquisa.md 2.8 KB
- assets/analise-swot.md 709 B
- references/analise-swot-salesforce.pdf 3142 KB
- references/analise-swot-sebrae.pdf 315 KB
- references/passo-a-passo-swot.pdf 506 KB
- references/pipeline.md 3.7 KB
- scripts/gerar-swot-visual.py 26 KB runs code
- scripts/swot_visual.html 19 KB
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.
- 12d ago First seen · 120 lines · 134 tokens per session scan A 859355476049
analise-swot is a skill published in the GitHub repository marioluciofjr/skills (16 stars, last pushed 14d ago), licensed Apache-2.0. It adds 134 tokens to every session and 1,927 once invoked, about $0.0007 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
ops-demo
CocoOps demo mode activator — populates .cocoplus/ops/demo/ with realistic mock data and sets cocoplus.toml [demo] enabled = true. Invoked via $ops demo.
map-explain
Produce a natural-language explanation of a specific Cortex function, business capability, or schema element from the committed knowledge graph.
cocoplus-off
Deactivate Full Assist Mode — removes all CocoPlus feature flags. Data files (memory, meter history, grove patterns) are preserved. Idempotent.
ops-suggest
Show time-aware CocoOps operational suggestions from the deterministic ops-suggest classifier. Usage: $ops suggest.
wisdom-keep
Protect a CocoWisdom entry from consolidation. Usage: $wisdom keep --id --text " ".
contract
Outcome-driven Cortex function development — declares a behavioral contract before generation begins, enforces evidence-tiered proof before $ship, and defends against the self-oracle evaluation failure mode.