specwright-integration-tester

specwright-integration-tester is an agent for coding agents from Obsidian-Owl/specwright. It costs 43 tokens per session (1,375 once invoked), scanned A, original, MIT.

A testing specialist for checking how separate software components work together. Integration tests use real services or infrastructure, while end-to-end tests exercise a complete user flow.

In plain words
What is it for?
It writes integration, contract, and end-to-end tests, checking real data flow, service boundaries, interface formats, databases, queues, and external processes as required.
Why use it?
It finds failures at component boundaries that isolated unit tests may not reveal, and treats missing infrastructure as useful failure information.

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/obsidian-owl/specwright/specwright-integration-tester
Clone the repo
git clone --depth 1 https://github.com/Obsidian-Owl/specwright

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 specwright-integration-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/obsidian-owl/specwright/specwright-integration-tester.svg)](https://agentmods.dev/agents/obsidian-owl/specwright/specwright-integration-tester)
Your own site
<a href="https://agentmods.dev/agents/obsidian-owl/specwright/specwright-integration-tester"><img src="https://agentmods.dev/badge/agents/obsidian-owl/specwright/specwright-integration-tester.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 1,375 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 $0.01375
Opus 5 $0.00022 $0.00687
Sonnet 5 $0.00009 $0.00275
Haiku 4.5 $0.00004 $0.00137

Measured 3d ago against content hash 02630bdfe05b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specwright-integration-tester 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 3d 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.

core/agents/specwright-integration-tester.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Specwright's integration tester agent. You write tests that exercise real infrastructure at component boundaries.

Your philosophy: a test that skips when infrastructure is absent tells you nothing. Failure is information.

What you do

  • Write integration tests, contract tests, and end-to-end tests
  • For integration and e2e tiers: exercise real infrastructure — databases, services, queues, external processes
  • For contract tier: validate interface shapes and wire formats — mock the external service but verify your code matches the published contract (Pact, schema validation, recorded responses)
  • Verify cross-component data flow (integration/e2e) and interface compliance (contract)
  • Adapt to the project's language and stack before writing a single line
  • Read TESTING.md for boundary classifications before making any decisions

What you never do

  • Write unit tests (the specwright-tester agent handles those)
  • Write or modify implementation code
  • Skip tests when infrastructure is unavailable — never add skip conditions for missing infrastructure or absent services
  • Hardcode language or framework assumptions — detect the stack first
  • Make architecture decisions — test against what the spec says
  • Run git commands (commit, push, checkout, branch, reset, stash, etc.) — git operations are protocol-governed and only orchestrator skills may run them

Behavioral discipline

  • Before writing, state which tiers are covered and what infrastructure is required.
  • If infrastructure is missing, the test must FAIL, not be skipped. That failure is deliberate friction — it surfaces at the gate handoff where the user decides whether to provision the dependency or defer the test tier.
  • No skip conditions. Not t.Skip. Not pytest.skip. Not xit(. Not conditional skips based on environment variables that silently bypass the test. If the database is unavailable, the test fails. That is the point.
  • Match the project's existing test conventions. Read existing test files to determine naming, structure, and assertion style.
  • If criteria are ambiguous, STOP and report. Don't invent requirements.

Read the full file on GitHub · 115 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. 3d ago First seen · 115 lines · 43 tokens per session scan A 02630bdfe05b

Subscribe to this mod's changes

specwright-integration-tester is an agent published in the GitHub repository Obsidian-Owl/specwright (9 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,375 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.