verifica-prima-di-completare

verifica-prima-di-completare is a skill for Claude Code, Codex from thomascasali/claude-kb-workflow. It costs 94 tokens per session (761 once invoked), scanned A, original, MIT.

A verification rule for checking the result with a fresh command before calling a coding task complete, fixed, working, or ready to deploy.

In plain words
What is it for?
Use it after code changes to choose and run the relevant test, build, lint, type-check, request, or browser check.
Why use it?
It prevents completion claims based only on assumptions or partial checks. The agent must read the full output and exit status before reporting success.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after code changes to choose and run the relevant test, build, lint, type-check, request, or browser check.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thomascasali/claude-kb-workflow/verifica-prima-di-completare
Install

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.

Any agent
npx skills add thomascasali/claude-kb-workflow --skill verifica-prima-di-completare
Clone the repo
git clone --depth 1 https://github.com/thomascasali/claude-kb-workflow

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for verifica-prima-di-completare

README.md
[![agentmods](https://agentmods.dev/badge/skills/thomascasali/claude-kb-workflow/verifica-prima-di-completare/github.svg)](https://agentmods.dev/skills/thomascasali/claude-kb-workflow/verifica-prima-di-completare)
Your own site
<a href="https://agentmods.dev/skills/thomascasali/claude-kb-workflow/verifica-prima-di-completare"><img src="https://agentmods.dev/badge/skills/thomascasali/claude-kb-workflow/verifica-prima-di-completare/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.

agentmods 80×15 button for verifica-prima-di-completare

Your own site · 80×15
<a href="https://agentmods.dev/skills/thomascasali/claude-kb-workflow/verifica-prima-di-completare"><img src="https://agentmods.dev/badge/skills/thomascasali/claude-kb-workflow/verifica-prima-di-completare.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 761 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00094 $0.00761
Opus 5 $0.00047 $0.00380
Sonnet 5 $0.00019 $0.00152
Haiku 4.5 $0.00009 $0.00076

Measured 11d ago against content hash 790034637893, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

verifica-prima-di-completare scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. **Identifica** il comando che prova la claim (test, build, lint, type-check, curl, navigazione browser)
skills/verifica-prima-di-completare/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verifica prima di completare

Principio: l'evidenza precede la dichiarazione di "fatto".

La regola

Niente claim di completamento senza evidenza fresca dell'esecuzione.

Prima di scrivere "fatto / risolto / funziona / pronto":

  1. Identifica il comando che prova la claim (test, build, lint, type-check, curl, navigazione browser)
  2. Esegui il comando completo (non un subset, non da cache vecchia)
  3. Leggi l'output integrale e l'exit code
  4. Conferma che l'output corrisponda alla claim
  5. Solo allora comunica il successo

Red flag linguistici

Se stai per scrivere queste parole senza aver verificato, fermati:

  • "dovrebbe funzionare"
  • "probabilmente"
  • "sembra funzionare"
  • "il fix è semplice e non rompe nulla"
  • "ho aggiornato X, ora dovrebbe andare"

Queste frasi indicano che stai per dichiarare done senza prova.

Rationalizzazioni da bloccare

Pensiero Realtà
"Il lint passa, quindi funziona" Linter ≠ compiler ≠ test ≠ runtime
"Il type-check passa, quindi funziona" Compila ≠ funziona
"Il test unitario passa" Test unit ≠ integrazione ≠ E2E
"L'agente ha detto che ha finito" Richiede verifica indipendente
"L'ho già verificato 10 minuti fa" Lo stato può essere cambiato — rifai
"Ho fretta" Falsi positivi costano più tempo di una verifica

Casi specifici del workflow

  • Modifiche backend (Laravel/Node): esegui i test rilevanti + un curl reale o chiamata dell'endpoint
  • Modifiche frontend (Vue/React): build + caricamento pagina nel browser (non solo HMR)
  • Modifiche Flutter: flutter analyze + build release per la piattaforma toccata
  • Modifiche Docker/Traefik: docker compose config + docker compose up + curl al servizio esposto
  • Modifiche KB / project-memory: rileggi il file dopo la scrittura, verifica frontmatter valido
  • Modifiche presentazioni didattiche: build + apertura in browser, verifica che le slide non siano vuote o rotte
  • Commit/push: dopo il push, verifica con git log origin/<branch> che il commit sia arrivato

Read the full file on GitHub · 63 lines

Changes

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.

  1. 11d ago First seen · 63 lines · 94 tokens per session scan A 790034637893

Subscribe to this mod's changes

verifica-prima-di-completare is a skill published in the GitHub repository thomascasali/claude-kb-workflow (2 stars, last pushed 16d ago), licensed MIT. It adds 94 tokens to every session and 761 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.