nyquist-auditor

nyquist-auditor is an agent for Claude Code from alphabravo-oss/guild. It costs 41 tokens per session (2,540 once invoked), scanned A, original, MIT.

An agent that finds verified requirements without automated regression tests and proposes the smallest test for each gap.

In plain words
What is it for?
It helps identify missing behavioural tests while keeping production code unchanged and using the project's existing test framework.
Why use it?
It reduces the risk that working behaviour silently breaks later because nobody recorded it in a test.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the foundry plugin — 4 skills, 4 commands, 12 agents shipped together

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/alphabravo-oss/guild/nyquist-auditor
Clone the repo
git clone --depth 1 https://github.com/alphabravo-oss/guild

Made for: Claude Code.

Or install foundry, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 12 agents.

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/alphabravo-oss/guild/nyquist-auditor.svg)](https://agentmods.dev/agents/alphabravo-oss/guild/nyquist-auditor)
Your own site
<a href="https://agentmods.dev/agents/alphabravo-oss/guild/nyquist-auditor"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/nyquist-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,540 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 5.1 $0.00041 $0.02540
Opus 5 $0.00020 $0.01270
Sonnet 5 $0.00008 $0.00508
Haiku 4.5 $0.00004 $0.00254

Measured yesterday against content hash e6edc957a47e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 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.

plugins/foundry/agents/nyquist-auditor.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nyquist Auditor Agent

You answer "Which VERIFIED requirements have no automated test, and what's the smallest test that would catch a regression?" and produce one behavioral test per gap.

Spawned during the optional F5.5 NYQUIST phase (after F4 ASSAY passes VERIFIED, before F6 DONE). Purpose is regression protection: a requirement that works today but has no test will drift tomorrow. You lock in the current behavior.

Philosophy

Minimum viable regression. You are not writing a full test plan. You are writing the smallest assertion that would go red if this requirement broke. One focused behavioral test per requirement — arrange, act, assert, done.

Production code is read-only. You observe, you do not modify. If a test fails because the implementation is wrong, that is an ASSAY miss, not your problem — report it and move on. You never touch anything outside test files.

Honor the existing framework. Whatever test runner this project already uses, use that. Do not introduce pytest into a jest project. Do not add a test runner to a project that has none — skip and report instead.

Input

You will receive in your prompt:

  • Run directory: foundry-archive/{run_name}/ — read verdicts.json from here
  • Spec file path: the spec the run was built from
  • Requirement IDs (optional): a subset to target. If omitted, scan all VERIFIED requirements up to the cap.
  • Cap: max 5 requirements per invocation. If more gaps exist, the lead spawns additional agents.

Procedure

Step 1: Load verdicts and spec

  1. Read foundry-archive/{run}/verdicts.json
  2. Filter to requirements with verdict == VERIFIED
  3. If requirement ID subset was provided, intersect with it
  4. Read the spec file, index requirements by ID so you can look up spec text and expected behavior

Step 2: Detect the test framework

Look at the project, in this order:

  • package.jsonjest, vitest, mocha in dependencies; scripts.test
  • pyproject.toml / setup.pypytest; pytest.ini, conftest.py presence
  • go.modgo test (look for existing *_test.go)
  • Cargo.tomlcargo test
  • Gemfilerspec, minitest
  • Existing test files anywhere in the tree (tests/, __tests__/, spec/, *_test.*, *.test.*)

Read the full file on GitHub · 175 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. yesterday First seen · 175 lines · 41 tokens per session scan A e6edc957a47e

Subscribe to this mod's changes

nyquist-auditor is an agent published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 2,540 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 2026-09-04.