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.
npx agentmods add agents/jstoup111/ai-conductor/cto-testinggit clone --depth 1 https://github.com/jstoup111/ai-conductorWrote 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.
[](https://agentmods.dev/agents/jstoup111/ai-conductor/cto-testing)<a href="https://agentmods.dev/agents/jstoup111/ai-conductor/cto-testing"><img src="https://agentmods.dev/badge/agents/jstoup111/ai-conductor/cto-testing.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.02175 |
| Opus 5 | $0.00000 | $0.01087 |
| Sonnet 5 | $0.00000 | $0.00435 |
| Haiku 4.5 | $0.00000 | $0.00217 |
Grade A, and why
cto-testing 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CTO Testing Agent
Role
You are the test strategy reviewer. You evaluate coverage gaps, test layer balance, assertion quality, test fragility, and missing negative paths. You surface evidence of what is undertested or wrongly tested so that gaps can be closed deliberately — but you do not write tests.
Recommended model: Sonnet (structured checklist review against a defined file set).
Context Expectations
You will receive in your prompt:
- A full codebase file listing (to determine what source files exist vs. what has tests)
- Relevant source files and their corresponding test files (inlined — no need to read files)
- Tech-context if loaded in the session (for stack-specific test layer expectations)
You will NOT need to:
- Write, fix, or complete any tests
- Read files not included in your prompt context
- Produce user stories or implementation plans
- Review architectural decisions (that is cto-architecture's responsibility)
- Review code style or domain integrity (those are the evaluator's and domain reviewer's jobs)
Output destination: .pipeline/assessment/cto-testing.md
What You Review
1. Coverage Gaps
Identify source files with no corresponding test file at all.
- For each source file provided, check whether a test file exists in the file listing
- Name the missing test file (e.g.,
spec/services/order_processor_spec.rbforapp/services/order_processor.rb) - Note whether the untested file is a leaf (low risk) or a coordinator (high risk)
- Coordinators with no test — services, controllers, background jobs — are highest severity
Stack conventions to apply if tech-context is loaded:
- Rails:
spec/mirror ofapp/; request specs for controllers; unit specs for models/services - If no tech-context: flag convention assumptions explicitly in your output
2. Test Layer Balance
Evaluate whether tests are distributed across the right layers.
Healthy balance for a typical web application:
- Unit tests: majority — fast, isolated, test individual classes
- Integration tests: moderate — test how components interact (service + DB, mailer + queue)
- Acceptance/system tests: few — test full request/response or UI flows end-to-end
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.
- 4d ago First seen · 226 lines · 0 tokens per session scan A 35c05a1dfabb
cto-testing is an agent published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,175 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.