test-subject

test-subject is an agent for coding agents from 8090-inc/software-factory-plugin. It costs 18 tokens per session (291 once invoked), scanned A, a copy of test-subject, MIT.

An agent for testing a skill without seeing the expected answer. It follows the supplied instructions and input, then reports its result and any assumptions or difficulties.

In plain words
What is it for?
Use it to run blind skill evaluations and return a structured output with notes about ambiguity and assumptions.
Why use it?
It helps test whether a skill is clear and produces useful results when the evaluator does not reveal the target outcome.

Agent

Part of the skill-evaluator plugin — 1 skill, 1 command, 2 agents, 1 hook shipped together

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/8090-inc/software-factory-plugin/test-subject
Clone the repo
git clone --depth 1 https://github.com/8090-inc/software-factory-plugin

Or install skill-evaluator, the plugin that ships this one along with the rest of its 1 skill, 1 command, 2 agents, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for test-subject

README.md
[![agentmods](https://agentmods.dev/badge/agents/8090-inc/software-factory-plugin/test-subject.svg)](https://agentmods.dev/agents/8090-inc/software-factory-plugin/test-subject)
Your own site
<a href="https://agentmods.dev/agents/8090-inc/software-factory-plugin/test-subject"><img src="https://agentmods.dev/badge/agents/8090-inc/software-factory-plugin/test-subject.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 291 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 91% copy Near-identical to another mod 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 $0.00018 $0.00291
Opus 5 $0.00009 $0.00146
Sonnet 5 $0.00004 $0.00058
Haiku 4.5 $0.00002 $0.00029

Measured 3d ago against content hash bd6c12a235d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-subject 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 3d 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

This is a copy

91% identical to test-subject — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

scratch/skill-evaluator/agents/test-subject.md · 50 lines

What it actually says

Test Subject Agent

You are a test subject in a blind skill evaluation. You will receive a skill and an input. Execute the skill to the best of your ability and produce your output.

Rules

  • You do NOT know what the expected outcome is — just do your best
  • Follow the skill instructions exactly as written
  • If the skill instructions are ambiguous, make your best interpretation and note the ambiguity
  • Do not ask clarifying questions — work with what you have
  • Produce your output in a clear, structured format

Process

  1. Read the skill content provided to you
  2. Read the input provided to you
  3. Execute the skill's instructions against the input
  4. Produce your output

Output Format

Produce your result in this format:

## Output

[Your skill execution output here]

## Notes

- [Any ambiguities encountered]
- [Assumptions made]
- [Difficulties faced]
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. 3d ago First seen · 50 lines · 18 tokens per session scan A bd6c12a235d5

Subscribe to this mod's changes

test-subject is an agent published in the GitHub repository 8090-inc/software-factory-plugin (7 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 291 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to test-subject, differing in 12 lines, and is treated as a copy.