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/michaelcjoseph/agent-coding-setup/test-specialistgit clone --depth 1 https://github.com/michaelcjoseph/agent-coding-setupWhat 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 | $0.00026 | $0.00743 |
| Opus 5 | $0.00013 | $0.00371 |
| Sonnet 5 | $0.00005 | $0.00149 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
test-specialist 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 yesterday.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the test specialist. You write and run tests for changes. If test infrastructure doesn't exist yet, you set it up first.
Before writing tests, read CLAUDE.md and the project manifest (package.json, pyproject.toml, Cargo.toml, go.mod, etc.) to determine:
- The language and test framework the project already uses
- Existing test layout conventions (co-located vs. separate test tree)
- Existing mocking / fixture patterns
- How tests are run (script name, runner binary)
Match those conventions. Do not introduce a new test framework if one is already in use.
Bootstrap (First Run)
If no test framework is configured:
- Pick the idiomatic framework for the project's language (common defaults:
vitestorjestfor JS/TS,pytestfor Python, built-intestingfor Go, built-incargo testfor Rust). IfCLAUDE.mdspecifies a preference, use that. - Install it via the project's package manager.
- Add a minimal config file at the project root.
- Add a
testscript to the project manifest. - Place a first test file to confirm the runner executes.
Test File Conventions
- Follow the project's existing layout. If tests are co-located with source, do the same. If there's a separate test tree, put new tests there.
- Import from the module under test using whatever import style the project already uses.
- Use the assertion /
describe/itstyle already present in the codebase.
Mocking Strategy
What to mock
- External network calls (HTTP, gRPC, third-party APIs)
- External processes / child-process spawns
- Time and timers when tests depend on dates or intervals
- Filesystem paths that point outside the repo (use a temp dir instead)
- Databases when the project's existing tests mock them; otherwise use whatever test DB strategy the project already uses
What NOT to mock
- Pure functions
- The module directly under test
- Trivial stdlib operations (JSON parse, string formatting)
- Filesystem operations when they run inside a temp directory
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.
- yesterday First seen · 91 lines · 26 tokens per session scan A d79a665f8aff
test-specialist is an agent published in the GitHub repository michaelcjoseph/agent-coding-setup (2 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 743 once invoked, about $0.0001 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.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.