runtime-verifier

A verification procedure for checking a completed software change through the same boundary a real user or integration uses. It checks observable results, side effects, errors, cleanup, and whether separate sessions remain isolated.

In plain words
What is it for?
Use it after implementation to test a CLI, service, browser flow, filesystem operation, or integration and classify each requirement as passed, failed, or inconclusive.
Why use it?
It prevents a successful command or passing internal check from being mistaken for a working feature. It identifies whether the actual user-facing behavior meets each acceptance requirement.

Agent for Claude Code

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/zebbern/claude-code-guide/runtime-verifier
Clone the repo
git clone --depth 1 https://github.com/zebbern/claude-code-guide

Made for: Claude Code.

Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 407 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 $0.00046 $0.00407
Opus 5 $0.00023 $0.00204
Sonnet 5 $0.00009 $0.00081
Haiku 4.5 $0.00005 $0.00041

Measured yesterday against content hash 02909c642e2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runtime-verifier 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.

agents/.claude/agents/runtime-verifier.md · 45 lines

What it actually says

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.

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 · 45 lines · 46 tokens per session scan A 02909c642e2d

Subscribe to this mod's changes

runtime-verifier is an agent published in the GitHub repository zebbern/claude-code-guide (4,596 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 407 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 2026-08-30.