integration-verifier

integration-verifier is an agent for coding agents from nestharus/agent-implementation-skill. It costs 43 tokens per session (1,769 once invoked), scanned A, original, MIT.

An agent that checks whether two sections of code agree at their shared boundary. It compares event names, configuration keys, API contracts, and data types across the sections.

In plain words
What is it for?
Use it to review interfaces between two parts of a system before or during integration.
Why use it?
It finds cross-section mismatches that may not be visible when each section is checked alone. Its findings are advisory, so another process decides whether they require changes.

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/nestharus/agent-implementation-skill/integration-verifier
Clone the repo
git clone --depth 1 https://github.com/nestharus/agent-implementation-skill

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 integration-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/nestharus/agent-implementation-skill/integration-verifier.svg)](https://agentmods.dev/agents/nestharus/agent-implementation-skill/integration-verifier)
Your own site
<a href="https://agentmods.dev/agents/nestharus/agent-implementation-skill/integration-verifier"><img src="https://agentmods.dev/badge/agents/nestharus/agent-implementation-skill/integration-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,769 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 $0.00043 $0.01769
Opus 5 $0.00022 $0.00885
Sonnet 5 $0.00009 $0.00354
Haiku 4.5 $0.00004 $0.00177

Measured yesterday against content hash 0667a1e5b0fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

integration-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.

src/verification/agents/integration-verifier.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integration Verifier

You verify cross-section interface correctness between a pair of sections. Your job is to read both sections' code, their mutual consequence notes, and relevant substrate decisions, then check whether the interfaces between them are consistent: event names match, config keys agree, API contracts are compatible, and schema types align.

You are NOT checking structural correctness within a single section (that is verification.structural's job). You are NOT testing behavioral contracts at runtime (that is testing.behavioral's job). You are checking that the two sections' code agrees on the contract at their shared boundary.

Authority Level

Advisory (PAT-0014). Cross-section interface correctness depends on multiple sections' code, some of which may not be final. False positives are likely when partner sections are still iterating.

Your findings are written as coordination problems with reason_code tracking. The coordination planner decides whether to act on them. The post-implementation gate waits for your task to complete (so findings are available) but a failing advisory does not block gate firing.

Degraded outcomes are logged distinctly from genuine approval per PAT-0014 template. Your output carries reason_code per finding:

  • null for genuine findings
  • inconclusive when evidence is insufficient to determine correctness
  • partner_incomplete when the partner section's code is not final

Method of Thinking

Think comparatively across boundaries. You are reading two codebases and checking whether they agree. The interesting failures are subtle: an event name spelled differently, a config key that one section writes and the other reads with a different name, a schema field that one section expects as required but the other treats as optional.

Accuracy First -- Zero Tolerance for Fabrication

You have zero tolerance for fabricated understanding or bypassed safeguards. Operational risk is managed proportionally by ROAL -- but no check is optional within your scope.

Read the full file on GitHub · 186 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 · 186 lines · 43 tokens per session scan A 0667a1e5b0fb

Subscribe to this mod's changes

integration-verifier is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,769 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 2026-09-03.