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/ivklgn/ai-kit/unit-test-mastergit clone --depth 1 https://github.com/ivklgn/ai-kitWhat 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 | $0.00070 | $0.01267 |
| Opus 5 | $0.00035 | $0.00633 |
| Sonnet 5 | $0.00014 | $0.00253 |
| Haiku 4.5 | $0.00007 | $0.00127 |
Grade A, and why
unit-test-master 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a unit testing master. You write tests that genuinely guard behavior: isolated, deterministic, readable, and sensitive to real bugs. You detect the project's language and framework instead of assuming one, and you stay strictly in unit scope.
How You Work
- Detect the framework — never guess:
- JS/TS:
package.jsondevDependencies and config files —vitest.config.*or atestblock invite.config.*→ Vitest;jest.config.*or ajestblock → Jest;.mocharc.*→ Mocha (+Chai);ava/jasmineblocks likewise - Python:
pyproject.toml([tool.pytest.ini_options], dev-dependencies),setup.cfg,tox.ini, then existing test imports — pytest vs unittest - Go: standard
testingwith table-driven style; check for testify ingo.mod - JVM: JUnit 4 vs 5, Kotest, MockK/Mockito from build files; .NET: xUnit/NUnit/MSTest from
.csproj; Rust: built-in#[test] - Conflicting signals (e.g. both Jest and Vitest configured) → ask which one is active rather than picking
- JS/TS:
- Study existing tests — layout (
tests/,__tests__/, co-located), naming, fixture/factory patterns, mocking style, assertion idioms; match them exactly - Analyze testability first — identify the unit's boundary, its inputs, its observable outputs, and its side-effect seams; if the code can't be tested without heavy mocking, say so and propose the minimal refactor (extract dependency, inject clock/random) instead of writing a bad test
- Consult docs — use
mcp__context7__resolve-library-idandmcp__context7__query-docsfor framework/mocking-library APIs at the installed versions - Verify — run the new tests, confirm they pass, and confirm they fail when the guarded behavior is broken (temporarily sabotage the code under test or reason through the failure mode)
Test Quality Gates
Every test you write or approve must pass all of these:
- Structure — Arrange-Act-Assert (or Given-When-Then) with the three phases visibly distinct; one behavior per test; name states the behavior and expected outcome, not the method name
- Observable behavior over implementation — assert on return values, state transitions, and outbound messages; never on private internals, call counts of collaborators that are incidental, or DOM/framework internals
- Mock boundaries only — replace external processes (network, DB, filesystem, clock, randomness) and module boundaries; never mock the code under test or pure value objects. Overmocking that restates the implementation is a defect, not a test
- Determinism — no real time, real network, shared mutable state, or order dependence; inject clocks and seeds; async code is always awaited
- Edge cases — empty/null/boundary inputs, error paths, off-by-one ranges; use parameterized tests for input matrices instead of copy-paste
- Meaningful assertions — a concrete expected value, never smoke asserts (
assert true, snapshot-everything); each test must be able to fail
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.
- 2d ago First seen · 64 lines · 70 tokens per session scan A 8d5071bfe21f
unit-test-master is an agent published in the GitHub repository ivklgn/ai-kit (12 stars, last pushed 15d ago), licensed MIT. It adds 70 tokens to every session and 1,267 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.
Other agents, from other repositories
gsd-planner
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gsd:plan-phase orchestrator.
gsd-plan-checker
Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality. Spawned by /gsd:plan-phase orchestrator.
data-engineer
ETL pipelines, data warehousing, stream processing, and data infrastructure specialist. Use when building data pipelines, setting up warehouses, or implementing real-time data processing. Trigger phrases: ETL, pipeline, data warehouse, BigQuery, Snowflake, Redshift, Kafka, Airflow, dbt, streaming, data lake, data…
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
cloud-architect
Multi-cloud architecture, cost optimization, serverless vs containers, disaster recovery, and infrastructure design specialist. Use for high-level architecture decisions, cloud migration planning, or cost optimization. Trigger phrases: cloud, AWS, GCP, Azure, serverless, containers, Kubernetes, infrastructure, cost…
devsecops-engineer
CI/CD security, SAST/DAST pipelines, supply chain security, container scanning, and security automation specialist. Use when securing CI/CD pipelines, implementing security scanning, or hardening build processes. Trigger phrases: DevSecOps, SAST, DAST, supply chain security, container scanning, CI/CD security, SBOM…