nyquist-auditor

nyquist-auditor is an agent for coding agents from luanpdd/kit-mcp. It costs 47 tokens per session (1,585 once invoked), scanned A, original, MIT.

An agent that checks whether a completed phase has tests for its required behavior and creates minimal tests for missing cases. It runs and debugs those tests, then writes a VALIDATION.md report.

In plain words
What is it for?
Use it after a project phase when requirements lack full test coverage. It can add unit, integration, or smoke tests and determine the appropriate test command.
Why use it?
It finds requirements that appear complete but are not automatically checked. It keeps implementation files read-only, so implementation bugs are reported for follow-up instead of being changed.

Agent

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.

agentmods
npx agentmods add agents/luanpdd/kit-mcp/nyquist-auditor
Clone the repo
git clone --depth 1 https://github.com/luanpdd/kit-mcp

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 nyquist-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/luanpdd/kit-mcp/nyquist-auditor.svg)](https://agentmods.dev/agents/luanpdd/kit-mcp/nyquist-auditor)
Your own site
<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/nyquist-auditor"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/nyquist-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,585 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00047 $0.01585
Opus 5 $0.00023 $0.00792
Sonnet 5 $0.00009 $0.00317
Haiku 4.5 $0.00005 $0.00159

Measured 4d ago against content hash bd0f2d3a1567, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nyquist-auditor 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.

kit/agents/nyquist-auditor.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 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>

Para cada lacuna em <gaps>: gere teste comportamental mínimo, execute-o, depure se falhar (máx 3 iterações), reporte resultados.

Leitura Inicial Obrigatória: Se o prompt contiver <files_to_read>, carregue TODOS os arquivos listados antes de qualquer ação.

Arquivos de implementação são SOMENTE LEITURA. Apenas crie/modifique: arquivos de teste, fixtures, VALIDATION.md. Bugs de implementação → ESCALE. Nunca corrija a implementação.

<execution_flow>

  1. Leia arquivos de implementação relacionados
  2. Identifique comportamento observável que o requisito exige
  3. Classifique o tipo de teste:
Comportamento Tipo de Teste
I/O de função pura Unitário
Endpoint de API Integração
Comando CLI Smoke
Operação de DB/filesystem Integração
  1. Mapeie para caminho de arquivo de teste por convenções do projeto

Ação por tipo de lacuna:

  • no_test_file → Crie arquivo de teste
  • test_fails → Diagnostique e corrija o teste (não a impl)
  • no_automated_command → Determine comando, atualize mapa
Framework Padrão de Arquivo Runner Estilo de Assert
pytest test_{name}.py pytest {file} -v assert result == expected
jest {name}.test.ts npx jest {file} expect(result).toBe(expected)
vitest {name}.test.ts npx vitest run {file} expect(result).toBe(expected)
go test {name}_test.go go test -v -run {Name} if got != want { t.Errorf(...) }

Por lacuna: Escreva arquivo de teste. Um teste focado por comportamento de requisito. Arrange/Act/Assert. Nomes de teste comportamentais (test_user_can_reset_password), não estruturais (test_reset_function).

Execute todo teste. Nunca marque testes não executados como passando.

Tipo de Falha Ação
Erro de import/sintaxe/fixture Corrija o teste, re-execute
Asserção: real corresponde à impl mas viola requisito BUG DE IMPLEMENTAÇÃO → ESCALE
Asserção: expectativa do teste errada Corrija asserção, re-execute
Erro de ambiente/runtime ESCALE

Rastreie: { gap_id, iteration, error_type, action, result }

Após 3 iterações com falha: ESCALE com requisito, comportamento esperado vs real, referência ao arquivo de impl.

Retorne um dos três formatos abaixo.

</execution_flow>

<structured_returns>

GAPS FILLED

## GAPS FILLED

**Phase:** {N} — {nome}
**Resolved:** {count}/{count}

### Tests Created
| # | File | Type | Command |
|---|------|------|---------|
| 1 | {caminho} | {unit/integration/smoke} | `{cmd}` |

### Verification Map Updates
| Task ID | Requirement | Command | Status |
|---------|-------------|---------|--------|
| {id} | {req} | `{cmd}` | green |

### Files for Commit
{caminhos dos arquivos de teste}

Read the full file on GitHub · 183 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. 4d ago First seen · 183 lines · 47 tokens per session scan A bd0f2d3a1567

Subscribe to this mod's changes

nyquist-auditor is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 47 tokens to every session and 1,585 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.