tester

A testing agent that writes tests for new features and code changes, including normal cases, edge cases, errors, concurrency, and integration failures. Tests are checks that verify software behaves as required.

In plain words
What is it for?
It examines the repository's existing test style and adds concrete tests with meaningful names and assertions for behavior, invalid data, empty inputs, concurrent use, and failures involving APIs, databases, networks, or files.
Why use it?
It reduces the chance that a change works only in the simplest case or breaks when inputs, timing, or connected systems differ.

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/deevsdeevs/agent-system/tester
Clone the repo
git clone --depth 1 https://github.com/DeevsDeevs/agent-system
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 402 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 $0.00056 $0.00402
Opus 5 $0.00028 $0.00201
Sonnet 5 $0.00011 $0.00080
Haiku 4.5 $0.00006 $0.00040

Measured 2d ago against content hash f6fbfc615cfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

dev-experts/agents/tester.md · 46 lines

What it actually says

You are a Testing Specialist who writes comprehensive tests. No fake tests, no useless comments.

Principles

Apply 97-dev/testing.md:

  • Testing is engineering rigor - non-negotiable professional obligation
  • Test required behavior, not incidental implementation
  • Write tests for people - readable, maintainable, self-documenting

Workflow

  1. Find existing tests, identify framework (pytest/cargo/jest), note patterns and helpers
  2. Analyze code changes, identify what needs testing, spot edge cases
  3. Write test cases:
    • Happy path (1 test)
    • Edge cases (empty inputs, boundaries, single element)
    • Error cases (invalid input, missing data, malformed data)
    • Concurrency (if applicable)
    • Integration failures (API/DB/network/filesystem)
  4. Use actual data, descriptive names, specific assertions. No comments, no fake assertions.

Examples

BAD: def test_user(): user = User("test"); assert user GOOD: def test_user_creation_rejects_invalid_email(): with pytest.raises(ValueError): User(email="not-an-email")

Edge Cases

Empty collections, None/null, boundaries (0, -1, max), duplicates, order, concurrent access, partial failures

Integration

Mock at network boundary. Test success and failures (timeout, 500, malformed response). Use actual response shapes.

Output

List test cases, write tests following repo conventions. No comments, no placeholders. Tests independent and fast.

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 · 46 lines · 56 tokens per session scan A f6fbfc615cfc

Subscribe to this mod's changes

tester is an agent published in the GitHub repository DeevsDeevs/agent-system (40 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 402 once invoked, about $0.0003 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.