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/luanpdd/kit-mcpWrote 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/luanpdd/kit-mcp/expresso)<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/expresso"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/expresso.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.00697 |
| Opus 5 | $0.00015 | $0.00349 |
| Sonnet 5 | $0.00006 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
expresso 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 4d 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.
What it actually says
Modo expresso é o mesmo sistema com um caminho mais curto:
- Invoca planner (modo rápido) + executor(s)
- Tarefas expressas ficam em
.planning/quick/separado das fases planejadas - Atualiza tabela "Quick Tasks Completed" do STATE.md (NÃO ROADMAP.md)
Padrão: Pula pesquisa, discussão, plan-checker, verificador. Use quando você sabe exatamente o que fazer.
Flag --discuss: Fase de discussão leve antes do planejamento. Apresenta hipóteses, esclarece áreas cinzentas, captura decisões em CONTEXT.md. Use quando a tarefa tem ambiguidade que vale a pena resolver antecipadamente.
Flag --full: Habilita verificação de plano (máximo 2 iterações) e verificação pós-execução. Use quando você quer garantias de qualidade sem a cerimônia completa de milestone.
Flag --research: Invoca um agente de pesquisa focado antes do planejamento. Investiga abordagens de implementação, opções de biblioteca e armadilhas para a tarefa. Use quando não tem certeza da melhor abordagem.
Flags são combináveis: --discuss --research --full dá discussão + pesquisa + verificação de plano + verificação.
Modelo inline (opcional): um token de modelo no fim (opus|sonnet|haiku|inherit ou id do runtime) força o modelo do executor só nesta execução — ex.: /expresso "ajuste trivial" haiku. Override de prioridade máxima sobre o perfil (ver model-profile-resolution.md). Absorvido do execute <plano> <modelo> do improve.
Quando usar
- ✅ Tarefa concreta de 5-30 min com necessidade de commit limpo + state tracking
- ✅ Hotfix com ambiguidade (use
--discuss) - ✅ Decisão técnica pequena com opções (use
--research) - ❌ Trivialidade de 1 minuto — use
/rapido - ❌ Trabalho que requer fases formais e verificação — use
/planejar-fase - 🤔 Em dúvida? →
/fazer "descrição"roteia automaticamente
<execution_context> @./.claude/framework/workflows/quick.md </execution_context>
Arquivos de contexto são resolvidos dentro do workflow (init quick) e delegados via blocos <files_to_read>.
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.
- 4d ago First seen · 59 lines · 30 tokens per session scan A 4f6023a558f3
expresso is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 697 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 2026-09-03.
Other commands, from other repositories
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
commit-claude-config
Version the Solana AI Kit config in git (un-ignores .claude/, CLAUDE.md, .mcp.json, .gitmodules and commits them).
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
feat
Quick feature commit. Use for new feature, add feature, implement, create new.
step6-ship
Pipeline Step 6 — Ship the completed phase: commit, update roadmap, capture postmortem, optionally push and create PR.