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/analyze)<a href="https://agentmods.dev/commands/felvieira/claude-skills-fv/analyze"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/analyze/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/analyze"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/analyze.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 | $0.00038 | $0.01785 |
| Opus 5 | $0.00019 | $0.00892 |
| Sonnet 5 | $0.00008 | $0.00357 |
| Haiku 4.5 | $0.00004 | $0.00178 |
Grade A, and why
analyze 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/analyze — Cross-Artifact Consistency Check
Objetivo: validar coerência entre os artefatos do pipeline (memory/constitution.md → docs/specs/*.md → docs/plan/*.md ou ADRs → issues do tracker) antes de mandar /build ou /auto. Read-only. Output estruturado, sem modificar arquivos.
Inspirado em github/spec-kit — /speckit.analyze.
Quando usar:
- depois de
/to-issuese antes de/build - antes de release major (
/ship) como gate adicional - depois de mudança grande na constituição (ver o que ficou inconsistente)
Quando NÃO usar:
- bug fix pontual (overhead desnecessário)
- pipeline ainda incompleto (não tem spec OU plan OU issues) → rode primeiro o que falta
Skill ativada: Reviewer (skill 11) em modo "cross-artifact auditor".
Garantias
- STRICTLY READ-ONLY — não modifica nenhum arquivo
- Constituição é não-negociável — conflito constituição ↔ outro artefato sempre vira CRITICAL
- Sem heurística destrutiva — não sugere apagar/reescrever; apenas reporta
Pré-requisitos
Detectar artefatos:
CONSTITUTION="memory/constitution.md"
SPEC_DIR="docs/specs"
PLAN_DIR="docs/plan"
ADR_DIR="docs/adr"
# fallback: se não houver docs/specs, tentar .taskmaster/docs/prd.md
[ -d "$SPEC_DIR" ] || SPEC_FALLBACK=".taskmaster/docs/prd.md"
# issues do tracker
gh issue list --label needs-triage --json number,title,body --limit 100 > /tmp/issues.json 2>/dev/null || true
Abortar se faltar qualquer dos 3 (spec, plan, issues) — pedir o usuário rodar o passo que falta. Constituição é fortemente recomendada mas não obrigatória.
Processo (6 passos)
1. Carregar artefatos (progressive disclosure)
Não carregue tudo de uma vez. Ler apenas as seções relevantes por artefato:
- Constituição: seções marcadas "Owner:" + princípios numerados
- Spec: Problem Statement, User Stories, Out of Scope, Implementation Decisions
- Plan/ADRs: Decisões registradas + status
- Issues: título + body + label (não comentários)
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 · 184 lines · 38 tokens per session scan A 2eb07fe1685a
analyze is a command published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 1,785 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.