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/pipeline-discovery)<a href="https://agentmods.dev/commands/felvieira/claude-skills-fv/pipeline-discovery"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/pipeline-discovery/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/pipeline-discovery"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/pipeline-discovery.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 | $0.00055 | $0.01662 |
| Opus 5 | $0.00028 | $0.00831 |
| Sonnet 5 | $0.00011 | $0.00332 |
| Haiku 4.5 | $0.00006 | $0.00166 |
Grade A, and why
pipeline-discovery 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pipeline-discovery — Fluxo Discovery + Vertical Slicing + TDD
Objetivo: Pipeline end-to-end completo com fase de discovery formal (grill-me), PRD publicado em issue tracker, quebra em vertical slices independentes, execução paralela com TDD por slice, e release final.
Variante "premium" do /pipeline. Use para feature grande/nova/ambígua. Para feature pequena/clara, /pipeline clássico ainda é mais direto.
Quando usar
- feature grande nova (>1 sprint de trabalho)
- briefing vago, equipe nova com a área, ou stakeholder indeciso
- vai paralelizar com 2+ workers (
/loop --worktree --parallel N) - precisa publicar issues no GitHub/Linear/Jira para tracking
- código de produção crítico que merece TDD enforced
Quando NÃO usar (use /pipeline clássico)
- bug fix
- spec já existe e está aprovada
- feature pequena (<3 dias) que não precisa de issue tracker
- spike/POC throwaway
Skill ativada
Orchestrator (skill 09) coordena 6 fases sequenciais.
Fluxo (com gates de aprovação humana obrigatórios)
1. /grill-me → entendimento mútuo via interrogatório
↓ STOP: convergência detectada → confirmar com usuário antes de prosseguir
2. /to-prd → rascunho do PRD montado a partir do contexto
↓ STOP: apresentar rascunho do PRD → AGUARDAR aprovação explícita antes de publicar no issue tracker
3. /to-issues → propor quebra em N vertical slices
↓ STOP: apresentar tabela de slices (título, HITL/AFK, blocked-by) → AGUARDAR aprovação antes de publicar issues
4. (Opcional) skill 38 → Architecture Deepener avalia se precisa refactor antes
↓ STOP se candidato for proposto: aguardar aprovação antes de despachar skill 23
5. /loop --worktree → N workers em paralelo, cada um pega 1 slice
--parallel N (cria N worktrees + commits — gate humano OBRIGATÓRIO antes de disparar)
↓
Por slice:
- /build → DB + back + front juntos (vertical, nunca layered)
- skill 37 (TDD) → red-green-refactor por comportamento
- skill 05 (QA) → edge cases não cobertos pelo TDD
- /review → Reviewer + Security
- merge se Critical/High zerado
↓
6. /ship → release final quando todos os slices mergeados
↓ STOP: apresentar changelog → AGUARDAR aprovação antes de tag/deploy
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 · 131 lines · 55 tokens per session scan A c20774e19ee4
pipeline-discovery is a command published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 1,662 once invoked, about $0.0003 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
bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.
usage-add
PitWay: Accumulate measured planning or qa token usage onto a milestone.
dashboard
Generar dashboard HTML local con métricas de eficiencia del proyecto SDD.
hub-tdd
TDD workflow for MCP Hub implementation. Types → Tests (red) → Implementation (green) with git gates.
eval
Evaluate and improve one healthcare agent's system prompt. Run up to 5 iterations of: prepare fixed questions -> answer -> judge -> improve -> re-score -> commit if better.
tdd
A command that follows test-driven development (TDD), a method where you write tests before the code they check. It moves through writing a failing test, adding the smallest implementation, and then improving the code.