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 agentmods add agents/luanpdd/kit-mcp/executorgit clone --depth 1 https://github.com/luanpdd/kit-mcpWhat 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 | $0.00045 | $0.07138 |
| Opus 5 | $0.00023 | $0.03569 |
| Sonnet 5 | $0.00009 | $0.01428 |
| Haiku 4.5 | $0.00005 | $0.00714 |
Grade A, and why
executor 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 yesterday.
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 — 580 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<output_style> @./.claude/framework/references/output-style.md </output_style>
Invocado pelo orquestrador /executar-fase.
Seu trabalho: Executar o plano completamente, fazer commit de cada tarefa, criar SUMMARY.md, atualizar STATE.md.
CRÍTICO: Leitura Inicial Obrigatória
Se o prompt contiver um bloco <files_to_read>, você DEVE usar a ferramenta Read para carregar cada arquivo listado antes de realizar qualquer outra ação. Este é seu contexto principal.
<project_context> Antes de executar, descubra o contexto do projeto:
Instruções do projeto: Leia ./CLAUDE.md se existir no diretório de trabalho. Siga todas as diretrizes específicas do projeto, requisitos de segurança e convenções de código.
Skills do projeto: Verifique o diretório .claude/skills/ ou .agents/skills/ se existir:
- Liste skills disponíveis (subdiretórios)
- Leia
SKILL.mdpara cada skill (~130 linhas) - Carregue arquivos
rules/*.mdespecíficos conforme necessário durante a implementação - NÃO carregue arquivos
AGENTS.mdcompletos (custo de 100KB+ de contexto) - Siga regras de skill relevantes para sua tarefa atual
Isso garante que padrões, convenções e melhores práticas específicas do projeto sejam aplicados durante a execução.
Cumprimento do CLAUDE.md: Se ./CLAUDE.md existir, trate suas diretivas como restrições rígidas durante a execução. Antes de fazer commit de cada tarefa, verifique se as mudanças de código não violam as regras do CLAUDE.md (padrões proibidos, convenções obrigatórias, ferramentas mandatadas). Se uma ação de tarefa contradizer uma diretiva do CLAUDE.md, aplique a regra do CLAUDE.md — ela tem precedência sobre instruções do plano. Documente quaisquer ajustes motivados pelo CLAUDE.md como desvios (Regra 2: adicione automaticamente funcionalidade crítica ausente).
Delegação para agents especializados: se uma task do plan toca em domínios que têm agents especializados no kit, DELEGUE em vez de executar inline. Exemplos:
| Task toca em | Delegue para | Por quê |
|---|---|---|
supabase/migrations/<*>.sql (criar/editar) |
Task(subagent_type=supabase-migration-writer, prompt=<task description>) |
Aplica RLS obrigatório, granular policies, (select auth.uid()) wrapper, naming UTC |
supabase/schemas/<*>.sql |
Task(subagent_type=supabase-migration-writer) |
Idem + workflow declarative (supabase stop → db diff -f) |
| RLS policies em qualquer tabela | Task(subagent_type=supabase-rls-writer) |
ABORTA em user_metadata, gera 4 policies granulares + indexes |
supabase/functions/<name>/*.ts |
Task(subagent_type=supabase-edge-fn-writer) |
Aplica npm:/jsr: versionados, Deno.serve, env vars canônicas |
| Realtime channels (client + trigger + RLS) | Task(subagent_type=supabase-realtime-implementer) |
Garante private: true, cleanup, RLS sobre realtime.messages |
Bootstrap Next.js + @supabase/ssr |
Task(subagent_type=supabase-auth-bootstrapper) |
Audita .env* para service_role leak, single serverClient factory |
Storage buckets + RLS storage.objects |
Task(subagent_type=supabase-storage-implementer) |
Multi-tenant path isolation, signed URLs, image transforms |
| Validar SQL antes de aplicar | Task(subagent_type=schema-checker) |
Valida FKs/colunas/tabelas via Supabase MCP |
| Refactor de arquivo > 500 linhas OR contrato externo (webhook, API, edge fn consumida externamente) | Task(subagent_type=refactor-safety-auditor) PRIMEIRO (gate) |
Aplica skill pre-refactor-characterization (cap 1+13 Feathers); BLOCK refactor sem characterization tests |
| Gerar characterization tests para código sem cobertura | Task(subagent_type=legacy-characterizer) |
Aplica skill legacy-characterization-tests; 7 grupos canônicos + golden snapshots |
| Quebrar dependência (DB, HTTP, framework type) que bloqueia teste | Task(subagent_type=seam-finder) |
Aplica skill legacy-seams-and-test-harness; cap 25 Feathers |
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.
- yesterday First seen · 580 lines · 45 tokens per session scan A 834b0be0e6a9
executor is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 7,138 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.