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/felvieira/claude-skills-fvWrote 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/commands/felvieira/claude-skills-fv/aside)<a href="https://agentmods.dev/commands/felvieira/claude-skills-fv/aside"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/aside/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/commands/felvieira/claude-skills-fv/aside"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/aside.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 | $0.00023 | $0.00638 |
| Opus 5 | $0.00012 | $0.00319 |
| Sonnet 5 | $0.00005 | $0.00128 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
aside 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 13d 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.
What it actually says
/aside — Pergunta Side Sem Contaminar Task
Objetivo: Responder pergunta tangencial à task atual sem:
- puxar contexto da task pra resposta
- atualizar tasks ativos
- atualizar
.bot/learned-skills/ou memória persistente - contaminar próxima ação com o desvio
A task atual fica intacta — /aside é uma janela isolada.
Quando usar:
- "rápido, antes de eu esquecer: como X funciona?" durante uma feature
- "tangentemente: Y é boa prática?" sem querer registrar como decisão do projeto
- pergunta de aprendizado pessoal que não deve virar instinct/skill
- evitar o anti-padrão de cada pergunta lateral virar contexto permanente
Quando NÃO usar:
- pergunta sobre a task atual — responda direto, contexto é relevante
- decisão arquitetural — esta merece registro (skill 10 documenter)
- bug encontrado — esta deve virar issue (
/to-issuesoumcp__ccd_session__spawn_task) - algo que vai mudar a task atual — não é aside, é mudança de escopo
Inputs:
<pergunta tangencial>(obrigatório)
Output:
- resposta isolada à pergunta
- nenhum efeito colateral:
- ❌ não adiciona task
- ❌ não atualiza
.bot/learned-skills/ - ❌ não atualiza memória persistente
- ❌ não menciona task atual na resposta
- ❌ não sugere próximo passo da task atual
Protocolo:
- Responder a pergunta direto, no estilo padrão do kit (≤300 tokens default).
- Citar fontes se relevante (Context7, docs oficiais).
- Não fazer referência à task em andamento.
- Não terminar com "voltando à task atual…" — assume-se que user retoma sozinho.
Anti-padrões:
- ❌ "Ótima pergunta! Voltando ao que estávamos fazendo…" — apenas responda e pare
- ❌ Atualizar memória/tasks por "completude" —
/asideé explícita declaração de isolamento - ❌ Misturar contexto: "isso me lembra que na sua task atual…" — quebra o isolamento
- ❌ Usar
/asidepra perguntas grandes — se exige investigação, abre uma sessão própria
Adaptado de: ECC /aside (MIT). Nosso ganho: integração explícita com policies/persistence.md (regras "Não Persistir") e respeitar context-engineering.md (hierarquia de contexto preservada).
Cross-refs: policies/persistence.md, policies/context-engineering.md, skill 08 (context-manager).
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.
- 13d ago First seen · 57 lines · 23 tokens per session scan A 063a34989534
aside is a command published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 23 tokens to every session and 638 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.