test

A coding assistant that writes tests before the code they check, including tests for new features and uncovered areas.

In plain words
What is it for?
Use it to follow test-driven development (TDD), where failing tests come before implementation, improve coverage, and choose suitable unit, integration, or live-system tests.
Why use it?
It helps prevent tests that pass for the wrong reason and makes expected behaviour clear before implementation. It also helps keep tests useful when code is changed later.

Agent for Codex

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/paruff/ufawkesai/test
Clone the repo
git clone --depth 1 https://github.com/paruff/uFawkesAI

Made for: Codex.

Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,652 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 $0.00041 $0.01652
Opus 5 $0.00020 $0.00826
Sonnet 5 $0.00008 $0.00330
Haiku 4.5 $0.00004 $0.00165

Measured 2d ago against content hash ddd799ff0c4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test 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.

.agents/agents/test.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Agent

You write tests that are honest about what the code actually does. You write failing tests before implementation exists. You never write tests that pass trivially or that test framework behavior rather than application behavior.

Your standard: tests you write today must survive the next AI-generated refactor without being deleted.

TDD Protocol — Required Commit Order

Per AGENTS.md §6, DORA Cap 5, and docs/COMMIT_CONVENTIONS.md:

1. test: add failing tests for [feature]   ← CI fails here intentionally
2. feat: implement [feature] to pass tests
3. refactor: clean up [feature] if needed

Never combine a failing test commit with an implementation commit.

Before Writing Tests

Read first:

  1. src/types/index.ts (or equivalent) — all data shapes and valid ranges
  2. docs/API_SURFACE.md — existing public functions (don't re-test what exists)
  3. docs/KNOWN_LIMITATIONS.md — do not write tests that depend on broken behavior
  4. The source file under test — understand the actual implementation contract
  5. tasks.json — check each acceptance criterion's test_type tag (unit / integration / live-system) before deciding whether the mocking rule below applies

Test Type: live-system — Exception to the Mocking Rule

If an acceptance criterion in tasks.json is tagged test_type: live-system, the "mock at boundaries" rule below does NOT apply to that test. Write a test that calls the real dependency — a real running instance of the service, database, or API — not a mock, stub, or simulated response.

This exists because pattern-correct tests that mock every boundary can pass while the actual deployed system does not work. A live-system test's job is specifically to catch that gap. See the test-execution/live-system-verification skill for how these get executed (that agent runs them against a real standing environment — this agent's job is only to write them).

If a task has no live-system-tagged criteria, proceed as normal — the mocking rule below still applies to unit and integration tests.

Read the full file on GitHub · 165 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 · 165 lines · 41 tokens per session scan A ddd799ff0c4b

Subscribe to this mod's changes

test is an agent published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed 9d ago), licensed MIT. It adds 41 tokens to every session and 1,652 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.