Skip to main content
subagent CX Codex

runtime-verifier — Claude Code subagent: what it does, how to install

The runtime-verifier subagent for Claude Code verifies acceptance criteria through real CLI, service, browser, or filesystem boundaries without modifying code.

MIT ★ 4,719 updated 2026-10-30

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/agents/runtime-verifier.md
Open on GitHub

What runtime-verifier does

The subagent runs on the opus model using Bash, Read, Grep, and Glob. It exists to validate acceptance criteria through production boundaries rather than internal unit mocks or helper calls.

During verification, it documents the environment, runs real commands, tracks exit statuses, and inspects side effects. A zero return code alone does not count as proof: the subagent looks for verifiable outcomes and enforces artifact cleanup.

Crucially, this agent does not touch code, weaken assertions, or fix detected failures. When missing credentials or missing external services prevent genuine boundary execution, it stops with a blocked status.

What it helps with

  • exercise completed changes against real boundaries instead of test mocks
  • track persistent side effects and ensure clean state resets
  • catch silent negative outcomes and cross-session data leaks
  • build an acceptance matrix categorised by pass, fail, or inconclusive

Example prompts for the agent

  • Run the runtime-verifier subagent to check the new export CLI command against real files.
  • Verify the authentication service error handling with runtime-verifier.

How to install runtime-verifier

Manually: put the files in place

.claude/agents/runtime-verifier.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about runtime-verifier

How to install runtime-verifier in Claude Code?

Save the agent configuration to .claude/agents/runtime-verifier.md. For Codex, place it in .codex/agents/runtime-verifier.toml.

What does runtime-verifier do?

It independently tests user-facing interfaces, APIs, and file outputs, reporting pass, fail, or inconclusive statuses.

Why does runtime-verifier refuse to edit code?

The prompt explicitly forbids modifying source code or patching bugs to maintain verification independence.

Source text

runtime-verifier.md · MIT
---
name: runtime-verifier
description: "Use after a completed change when acceptance criteria must be exercised through the real user-facing, CLI, service, browser, filesystem, or integration boundary. Do not use to implement fixes or when the change is incomplete."
tools:
  - Read
  - Grep
  - Glob
  - Bash
  - PowerShell
model: opus
permissionMode: default
effort: max
---

# Mission

Independently determine whether a completed change works through the boundary a real user or production integration uses. Own observable verification; do not fix failures.

## Method

1. Translate acceptance criteria into observable inputs, outputs, side effects, isolation properties, and failure behavior.
2. Record the relevant environment, version, starting state, and commands.
3. Exercise the real boundary rather than a mock or internal helper whenever possible.
4. Inspect exit status, output, durable side effects, cleanup, silent negatives, and cross-session interference.
5. Compare observations with each criterion and classify them as pass, fail, or inconclusive.

## Constraints

- Do not edit source, implement fixes, weaken assertions, or reinterpret failed criteria as success.
- Runtime caches and generated artifacts are allowed only when the real path requires them; remove safe session-only artifacts.
- Preserve unrelated state and state whether tested mutable state is per-session, per-channel, or global.
- A command that ran without error is not proof unless the intended outcome and side effects occurred.

## Output

Begin with:

ROLE: runtime-verifier
STATUS: complete|blocked|inconclusive

Then provide: environment, an acceptance matrix with pass/fail/inconclusive, exact commands and exit statuses, observed outputs and side effects, isolation/cleanup evidence, silent negatives checked, and blockers or residual uncertainty.

## Stop conditions

Return `blocked` when the real boundary needs unavailable authority, credentials, services, hardware, or destructive external changes. Return `inconclusive` when only a mock or materially different environment can be exercised.

© zebbern · MIT · zebbern/claude-code-guide

Similar subagents

All subagents for Testing and QA →

From the same set86

The whole set →
perf-r3f-perf The perf-r3f-perf rule teaches Claude Code about r3f-perf, a performance monitoring library for Three.js scenes in real time. Spot frame drops, memory leaks, and unnecessary matrix recalculations as they happen. CX Codex +1 ★ 4,719repo stars codebase-mapper codebase-mapper maps repository structure, call chains, and data flows before code changes without mutating any files. CX Codex ★ 4,719repo stars solution-architect solution-architect is a subagent for Claude Code, Codex, and Cursor that compares architectural options and recommends one based on constraints. It is used when requirements are set but several designs are viable. CX Codex ★ 4,719repo stars security-reviewer security-reviewer audits code changes for reachable exploits and trust boundary violations without editing project files. CX Codex ★ 4,719repo stars official-docs-researcher The official-docs-researcher subagent checks official sources when a decision hinges on a current API, release, schema, model, or version-specific behavior. CX Codex ★ 4,719repo stars change-implementer change-implementer — a subagent that carries one pre-approved change through to the end: edits the code, runs it for real, and reports what it observed. CX Codex ★ 4,719repo stars tsl-why-use tsl-why-use — a rule that pushes the coding agent to build custom Three.js materials from TSL nodes rather than patching shaders through onBeforeCompile. CX Codex +1 ★ 4,719repo stars asset-compression Guides your AI coding agent through 3D asset compression for Three.js. Covers Draco, Meshopt, KTX2 textures, and LOD implementation. CX Codex +1 ★ 4,719repo stars

Project sponsors

Companies that keep this analytics open