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.
npx skills add thomascasali/claude-kb-workflow --skill brainstorming-designgit clone --depth 1 https://github.com/thomascasali/claude-kb-workflowWrote 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/skills/thomascasali/claude-kb-workflow/brainstorming-design)<a href="https://agentmods.dev/skills/thomascasali/claude-kb-workflow/brainstorming-design"><img src="https://agentmods.dev/badge/skills/thomascasali/claude-kb-workflow/brainstorming-design/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/skills/thomascasali/claude-kb-workflow/brainstorming-design"><img src="https://agentmods.dev/badge/skills/thomascasali/claude-kb-workflow/brainstorming-design.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 | $0.00090 | $0.00910 |
| Opus 5 | $0.00045 | $0.00455 |
| Sonnet 5 | $0.00018 | $0.00182 |
| Haiku 4.5 | $0.00009 | $0.00091 |
Grade A, and why
brainstorming-design 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 10d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorming e design approval
Principio: per task non banali, allineati sul design prima di scrivere codice. Una domanda chiara ora evita un refactor domani.
Quando si attiva
✅ Sì:
- Nuova feature di rilievo (es. "aggiungi sistema notifiche push", "implementa OAuth")
- Nuovo progetto / nuova app
- Nuova presentazione didattica (struttura, target, livello dettaglio)
- Refactoring architetturale che tocca più moduli
- Task con 2+ strade plausibili e trade-off reali
- Modifiche che impattano API pubbliche o schema DB
❌ No:
- Bug fix puntuale
- Edit minimo già specificato dall'utente
- Aggiunta di una singola slide a una presentazione esistente
- Task con istruzioni già operative ("rinomina X in Y", "aggiungi questa funzione qui")
Processo
1. Esplora contesto (silenzioso)
Prima di chiedere, leggi:
- File rilevanti del progetto
project-memories/<progetto>.mdse esiste- Commit recenti (
git log --oneline -10) - Pattern simili già usati nel codebase
Questo evita di chiedere all'utente cose già visibili nel codice.
2. Domande di chiarimento (mirate, non a raffica)
Chiedi UNA cosa alla volta, preferibilmente con AskUserQuestion + opzioni concrete:
- Scopo: cosa risolve, per chi
- Vincoli: tempo, budget complessità, dipendenze già presenti
- Criterio di successo: come riconosciamo "fatto bene"
❌ Non fare interrogatori da 8 domande in un colpo. ✅ 2-3 domande chiave bastano per il 90% dei casi.
3. Proponi 2-3 approcci con trade-off
Per ogni approccio:
- Cosa cambia
- Pro / contro
- Effort stimato (S/M/L)
- Quale raccomandi e perché
Non proporre 5 alternative — l'utente non ha tempo di valutarle tutte. 2-3 è il giusto compromesso.
4. Presenta il design scelto
Suddiviso in sezioni leggibili. Per progetti grandi, chiedi approvazione sezione per sezione invece che presentare un wall of text.
5. Persisti il design se serve
Per progetti che durano più sessioni, salva la decisione in:
project-memories/<progetto>.md(sezione "Design decisions")- Un commit
docs:con il razionale
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.
- 10d ago First seen · 88 lines · 90 tokens per session scan A d79aaf9b5488
brainstorming-design is a skill published in the GitHub repository thomascasali/claude-kb-workflow (2 stars, last pushed 15d ago), licensed MIT. It adds 90 tokens to every session and 910 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
factory-design
Design-system discipline distilled across builds. Semantic token vocabulary (name intent, not palette position), CSS variables bridged into Tailwind, dark/light as a variable swap, single- vs two-layer token systems, component primitives as token consumers, when to promote a repeated utility cluster into a primitive…
factory-animation
Motion discipline distilled across builds. Attention as a fixed per-viewport budget, figure/ground separation (calm the ground, load motion into the figure), one focal point of motion per screen, diegetic-over-decorative test, trigger-on-intent-then-settle over perpetual loops, and the prefers-reduced-motion fallback.…
obsidian-graph-colors
Apply color groups to Obsidian's graph view so each topic branch has a distinct color. Use when the user says "color the graph", "graph colors", "update graph colors", "add topic color", or after creating new topic folders that need a color assignment.
slide-excellence
Multi-agent comprehensive slide review (visual + pedagogy + proofreading, plus TikZ / parity / substance conditionally). Use when user says "full review", "excellence pass", "comprehensive check", "review everything", "pre-release review", "slide excellence", or before teaching / shipping a deck. Fanout wrapper — for…
openkb-html-critic
Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…
product-research
Find and compare current FF&E candidates from a design brief, with sourced purchasing facts and optional CSV-library save. Use to research or source products; not to match from an image or pair coordinating items.