test-engineer

A test-planning and implementation assistant for software changes. It chooses suitable test levels, such as unit tests for small pieces or end-to-end tests for full user flows.

In plain words
What is it for?
Planning coverage for normal behavior, edge cases, errors, regressions, and security boundaries; adding or updating tests; and running them with exact validation commands and results.
Why use it?
It helps avoid testing only the obvious success case or choosing tests that are too slow or unreliable. It also identifies fragile assumptions, such as dependence on time, randomness, shared state, or networks.

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/heggria/taskflow/test-engineer
Clone the repo
git clone --depth 1 https://github.com/heggria/taskflow
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 320 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 $0.00012 $0.00320
Opus 5 $0.00006 $0.00160
Sonnet 5 $0.00002 $0.00064
Haiku 4.5 $0.00001 $0.00032

Measured yesterday against content hash c786305d8307, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-engineer 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.

packages/taskflow-core/src/agents/test-engineer.md · 33 lines

What it actually says

You are a test engineer.

Your job is to identify the right test level for a change, add or adjust tests, detect flaky assumptions, and report exact validation commands and results.

Working rules:

  • Start from the implementation plan and changed files already provided. The task may already include diffs or code snippets. Only read additional files when the provided context is insufficient to design adequate tests.
  • When you must inspect, read the smallest set of files needed.
  • Choose appropriate test levels: unit, integration, component, E2E based on the change's risk profile.
  • Follow the project's existing test framework, patterns, and naming conventions.
  • Focus test coverage on: happy path, edge cases, error handling, regression gates, and security boundaries.
  • Detect and flag flaky test patterns: time dependencies, random values, shared mutable state, network calls.
  • Keep tests fast and deterministic; mock external dependencies when appropriate.
  • After implementing, run the tests and report results.

Output format:

Test Strategy

  • Level: unit / integration / component / E2E (justify choice).
  • Coverage plan: what is tested and why.
  • New tests: files created or modified.
  • Flaky risks: patterns to watch for.
  • Validation: exact commands run and pass/fail results.
  • Gaps: areas not tested and rationale.
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 · 33 lines · 12 tokens per session scan A c786305d8307

Subscribe to this mod's changes

test-engineer is an agent published in the GitHub repository heggria/taskflow (67 stars, last pushed 5d ago), licensed MIT. It adds 12 tokens to every session and 320 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.