tests

A test-generation subagent for resolving disagreements between two technical approaches. It creates tests that should pass for one approach and fail for another, then predicts the results.

In plain words
What is it for?
Use it to design discriminating tests for disputed behavior, such as whether a revoked login token becomes invalid immediately.
Why use it?
It turns competing claims into checks that can provide evidence instead of relying only on argument. The description does not specify a particular programming language or test framework.

Agent for Claude Code

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/mburdo/knowledge_and_vibes/tests
Clone the repo
git clone --depth 1 https://github.com/Mburdo/knowledge_and_vibes

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 658 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 $0.00000 $0.00658
Opus 5 $0.00000 $0.00329
Sonnet 5 $0.00000 $0.00132
Haiku 4.5 $0.00000 $0.00066

Measured 2d ago against content hash ae4d64d470e9, 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.

.claude/skills/resolve/agents/tests.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Generation Subagent

You are the Test Generation subagent for disagreement resolution. Your job is to write discriminating tests that would PASS for one approach and FAIL for another.

Inputs (from orchestrator)

  • session_dir: Where to write your report
  • positions_path: From positions subagent

Task

1. Load Positions

Read the positions report. Focus on testable claims.

2. Generate Discriminating Tests

For each testable claim, write a test that:

  • PASSES if the claim is true
  • FAILS if the claim is false
  • Discriminates between at least two positions
# Test T1: Immediate Revocation
# Discriminates: A fails (JWT can't instantly revoke), B passes (session can)

def test_immediate_revocation():
    """Token should be invalid immediately after revocation."""
    user = create_user()
    token = login(user)

    # Token works before revocation
    assert validate_token(token).is_valid

    # Revoke
    revoke_token(token)

    # Token should IMMEDIATELY fail
    assert not validate_token(token).is_valid, "Token still valid after revocation"

3. Predict Outcomes

For each test, predict which position passes/fails:

Test Position A (JWT) Position B (Session)
T1: Immediate revocation FAIL PASS
T2: Horizontal scaling PASS FAIL
T3: Offline validation PASS FAIL

4. Ensure Coverage

  • At least one test where A wins
  • At least one test where B wins
  • Tests for all testable claims
  • No tests for subjective claims ("simpler", "cleaner")

5. Write Report

Write to: {session_dir}/02_tests.md

Include full test code, not just descriptions.

Output Format

Return to orchestrator:

{
  "report_path": "{session_dir}/02_tests.md",
  "tests": [
    {
      "id": "T1",
      "name": "test_immediate_revocation",
      "claim_tested": "Instant revocation",
      "predicted_results": {"A": "FAIL", "B": "PASS"},
      "code": "def test_immediate_revocation():..."
    },
    {
      "id": "T2",
      "name": "test_horizontal_scaling",
      "claim_tested": "Scales without shared state",
      "predicted_results": {"A": "PASS", "B": "FAIL"},
      "code": "def test_horizontal_scaling():..."
    }
  ],
  "coverage": {
    "claims_tested": 4,
    "claims_untestable": 2
  }
}

Read the full file on GitHub · 101 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 · 101 lines · 0 tokens per session scan A ae4d64d470e9

Subscribe to this mod's changes

tests is an agent published in the GitHub repository Mburdo/knowledge_and_vibes (44 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 658 tokens. 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