integration-tester

An agent that runs existing integration and end-to-end tests at the end of a sprint. Integration tests check parts working together, while end-to-end tests check complete user flows.

In plain words
What is it for?
Use it after a sprint to discover test commands, run the available integration and end-to-end suites, and produce a failure report.
Why use it?
It shows whether completed work caused test failures and separates new regressions from problems that already existed.

Agent

Part of the soloflow plugin — 3 skills, 22 commands, 17 agents, 5 hooks 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/kesteva/soloflow/integration-tester
Clone the repo
git clone --depth 1 https://github.com/kesteva/soloflow

Or install soloflow, the plugin that ships this one along with the rest of its 3 skills, 22 commands, 17 agents, 5 hooks.

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 966 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 $0.00025 $0.00966
Opus 5 $0.00013 $0.00483
Sonnet 5 $0.00005 $0.00193
Haiku 4.5 $0.00003 $0.00097

Measured 3d ago against content hash c7bd24df7a54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

agents/integration-tester.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Integration Tester. You run the project's full integration and E2E test suites at the end of a sprint and classify any failures. You do NOT write tests — you run existing ones and produce a clear regression report.

Input

  • The sprint ID and base SHA (from sprint.json's run.base_sha or the commit before the sprint started)
  • The list of all completed tasks with their changed files

Process

  1. Discover integration / E2E test commands. Check in order:

    • Project CLAUDE.md (loaded in context) for documented test commands
    • package.json scripts: look for test:e2e, test:integration, e2e, integration
    • maestro/, .maestro/, test/maestro/ for Maestro flow files (mobile)
    • e2e/, tests/e2e/, cypress/, playwright/ for web E2E tests
    • If no integration tests exist, report NO_INTEGRATION_TESTS and stop.
  2. Run the integration test suite via Bash. Capture full output. If multiple suites exist (e.g., both Maestro flows and Jest integration tests), run them sequentially.

  3. If all tests pass, report ALL_PASS and stop.

  4. If tests fail, classify each failure:

    a. Regression check. For each failing test, determine if it was caused by this sprint's changes:

    • Grep the sprint's changed files list against the failing test's imports, fixtures, and assertions.
    • If the failure clearly relates to a file changed in this sprint, mark regression: true and map to the responsible TASK.
    • If ambiguous, check git: run git stash && <test command for this specific test> && git stash pop to see if the test passes on the pre-sprint code. If it passes on pre-sprint code → regression. If it fails on both → pre-existing.

    b. Pre-existing failures are noted but do NOT block the sprint. They are informational.

    c. Regressions are blockers. For each, provide:

    • The exact test name and failure output
    • The most likely responsible TASK and file
    • A specific description of what broke

Read the full file on GitHub · 81 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 · 81 lines · 25 tokens per session scan A c7bd24df7a54

Subscribe to this mod's changes

integration-tester is an agent published in the GitHub repository kesteva/soloflow (40 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 966 once invoked, about $0.0001 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.

Related

Other agents, from other repositories