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/insights)<a href="https://agentmods.dev/commands/felvieira/claude-skills-fv/insights"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/insights/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/insights"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/insights.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 | $0.00046 | $0.02049 |
| Opus 5 | $0.00023 | $0.01025 |
| Sonnet 5 | $0.00009 | $0.00410 |
| Haiku 4.5 | $0.00005 | $0.00205 |
Grade A, and why
insights 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/insights — Recomendações Baseadas em Uso Real
Em uma frase: lê os JSONLs de telemetria dos hooks desta sessão (e sessões recentes) e recomenda o que configurar, calibrar ou desabilitar.
Inspiração: /Insights mencionado em "Claude Code Was Confusing Me Until I Found This One Plugin Nobody Talks About" (Nitin Gavhane, May 2026) — analisa últimas 30 dias de uso e recomenda automações. Nossa versão lê os dados que o kit já coleta.
Quando usar
- Após 1-2 semanas de uso do kit — dados suficientes pra padrões emergirem
- Quando hooks parecem disparar demais ou de menos
- Antes de migrar de
standard→strictouminimal(ver impacto real) - "Quero saber o que o kit está fazendo por mim"
- Onboarding num projeto novo — ver o que o kit detectou de incomum
Fontes de dados lidas
| Arquivo | Hook origem | O que contém |
|---|---|---|
.bot/pre-execution-gate.jsonl |
UserPromptSubmit | decision, score, ambiguidade por prompt |
.bot/investigate-first-guard.jsonl |
PreToolUse | perguntas auto-descobríveis bloqueadas (labels) |
.bot/tool-usage.json |
PreToolUse | tools mais usados, reads repetidos, bytes lidos |
.bot/conflict-resolution.jsonl |
PostToolUse | conflitos de policy resolvidos |
.bot/session-events.jsonl |
PostToolUse | eventos de sessão (tool calls, stops, errors) |
.bot/hook-session.json |
vários | estado da sessão atual |
D:\claude-memory\logs\*.md |
Stop hook | logs das últimas sessões (se vault configurado) |
.bot/route-feedback.jsonl |
executores / decisão explícita | recomendações de composição aceitas, alteradas ou rejeitadas |
Protocolo de execução
Fase 1 — Coletar dados disponíveis
# Verificar quais arquivos de telemetria existem
ls -la .bot/*.jsonl .bot/*.json 2>/dev/null
Ler cada arquivo existente e agregar:
- Total de eventos por tipo
- Distribuição de decisions (pass_through / enrich / guided_enrich / concrete_bypass)
- Labels de perguntas bloqueadas pelo investigate-first-guard
- Tools mais chamados e com mais repetições
- Conflitos de policy mais frequentes
- Decisões de roteamento e plugins mais aceitos/alterados, via
node scripts/routing-insights.mjs --root . --json
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 · 191 lines · 46 tokens per session scan A 72b08a1e645b
insights is a command published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session and 2,049 once invoked, about $0.0002 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.