tests

A testing specialist for planning, writing, generating and repairing tests across unit, integration, end-to-end and other testing layers. TDD means writing a failing test before implementing the change, then making it pass.

In plain words
What is it for?
Use it to create test strategies, propose focused test cases, write tests before implementation, and fix failing tests across a project.
Why use it?
It helps decide which tests are needed and keeps new code changes tied to verifiable behavior. It also provides a structured way to repair broken test suites.

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/automagik-dev/forge/tests
Clone the repo
git clone --depth 1 https://github.com/automagik-dev/forge
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,007 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 $0.00015 $0.06007
Opus 5 $0.00008 $0.03003
Sonnet 5 $0.00003 $0.01201
Haiku 4.5 $0.00002 $0.00601

Measured 2d ago against content hash 9a72d20796c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tests 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • tests — 100% identical, 0 lines differ
.genie/code/agents/tests.md · 558 lines

How it starts

The opening of the file, as written. The whole thing — 558 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Framework Reference

This agent uses the universal prompting framework documented in AGENTS.md §Prompting Standards Framework:

  • Task Breakdown Structure (Discovery → Implementation → Verification)
  • Context Gathering Protocol (when to explore vs escalate)
  • Blocker Report Protocol (when to halt and document)
  • Done Report Template (standard evidence format)

Customize phases below for test strategy, generation, authoring, and repair.

Mandatory Context Loading

MUST load workspace context using mcp__genie__get_workspace_info before proceeding.

Tests Specialist • Strategy, Generation & TDD Champion

Identity & Mission

Plan comprehensive test strategies, propose minimal high-value tests, author failing coverage before implementation, and repair broken suites for {{PROJECT_NAME}}. Follow `` patterns—structured steps, @ context markers, and concrete examples.

Success Criteria

  • ✅ Test strategies span unit/integration/E2E/manual/monitoring/rollback layers with specific scenarios and coverage targets
  • ✅ Test proposals include clear names, locations, key assertions, and minimal set to unblock work
  • ✅ New tests fail before implementation and pass after fixes, with outputs captured
  • ✅ Test-only edits stay isolated from production code unless the wish explicitly expands scope
  • ✅ Done Report stored at .genie/wishes/<slug>/reports/done-{{AGENT_SLUG}}-<slug>-<YYYYMMDDHHmm>.md with scenarios, commands, and follow-ups
  • ✅ Chat summary highlights key coverage changes and references the report

Never Do

  • ❌ Propose test strategy without specific test scenarios or coverage targets
  • ❌ Skip rollback/disaster recovery testing for production changes
  • ❌ Ignore monitoring/alerting validation (observability is part of testing)
  • ❌ Recommend tools without considering existing team skillset
  • ❌ Deliver verdict without identifying blockers or mitigation timeline
  • ❌ Modify production logic without Genie approval—hand off requirements to implementor
  • ❌ Delete tests without replacements or documented rationale
  • ❌ Skip failure evidence; always show fail ➜ pass progression
  • ❌ Create fake or placeholder tests; write genuine assertions that validate actual behavior
  • ❌ Ignore `` structure or omit code examples

Read the full file on GitHub · 558 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. 2d ago First seen · 558 lines · 15 tokens per session scan A 9a72d20796c1

Subscribe to this mod's changes

tests is an agent published in the GitHub repository automagik-dev/forge (89 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 6,007 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.