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 skills add QBall-Inc/the-bulwark --skill test-classificationgit clone --depth 1 https://github.com/QBall-Inc/the-bulwarkWrote 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/skills/qball-inc/the-bulwark/test-classification)<a href="https://agentmods.dev/skills/qball-inc/the-bulwark/test-classification"><img src="https://agentmods.dev/badge/skills/qball-inc/the-bulwark/test-classification.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00014 | $0.02427 |
| Opus 5 | $0.00007 | $0.01213 |
| Sonnet 5 | $0.00003 | $0.00485 |
| Haiku 4.5 | $0.00001 | $0.00243 |
Grade A, and why
test-classification scanned grade A with 1 finding 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 7d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| Imports system modules (`child_process`, `fs`, `http`) | Note for risk assessment | Copies of this mod
1 near-identical copy found in the catalogue:
- test-classification — 92% identical, 641 lines differ
How it starts
The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Classification
Prompt template for surface-level test classification and triage. Designed for a Haiku sub-agent to quickly categorize test files and flag those needing deep analysis.
When to Use This Skill
This is an internal skill loaded by the orchestrator during Test Audit pipeline.
| Context | Action |
|---|---|
/test-audit invoked |
Orchestrator loads this skill for Stage 1 |
| Test Audit pipeline triggered by hook | Orchestrator loads this skill for Stage 1 |
| Need to classify test files | Load directly as prompt template for Haiku |
DO NOT use for:
- Direct user invocation (not user-invocable)
- Mock detection (use
mock-detectionskill) - Full audit synthesis (use
test-auditskill)
Role in Test Audit Pipeline
This skill provides the first stage prompt template:
test-audit (P0.8) orchestrates:
Stage 1: test-classification (Haiku) → classification YAML
Stage 2: mock-detection (Sonnet) → violations YAML
Stage 3: synthesis (Sonnet) → audit report
The orchestrator loads this skill and constructs a 4-part prompt for a general-purpose Haiku sub-agent.
4-Part Prompt Template
GOAL
Classify all test files in {target} by type and flag files needing deep analysis for mock appropriateness.
CONSTRAINTS
- Do NOT modify any files
- Classify every test file found
- Use filename-first classification (content validates)
- Flag mock+integration mismatches for deep analysis
- Use AST verification_lines as ground truth when provided in context (do NOT re-count). Only fall back to manual counting if AST data is unavailable.
- Complete within 30 tool calls
CONTEXT
Target directory: {target}
Test file patterns: *.test.*, *.spec.*, test_*, *.integration.*, *.e2e.*
Classification rules: See "Classification Logic" section below
Deep analysis triggers: See "needs_deep_analysis Triggers" section below
Line counting rules: See "Verification Line Counting" section below
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.
- 7d ago First seen · 332 lines · 14 tokens per session scan A 49436b034a3e
test-classification is a skill published in the GitHub repository QBall-Inc/the-bulwark (8 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 2,427 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
journey-simulation
Use when caller wants to observe how a stranger encounters a flow, artifact, or sandbox — triggers like "simulate a user journey", "test our onboarding / checkout / signup", "will my ICP convert", "how does a cold reader experience this README", "first-time user test", "cognitive walkthrough", or any request to…
black-box-test
Use as an INDEPENDENT tester agent to test another agent's intesting ticket from the OUTSIDE — never your own, and never from the implementation diff. You test from the operational test contract + acceptance criteria only (never HOW it was built), writing automated tests that invoke the changed surfaces and recording…
java-conventions
Use when a ticket adds or changes Java code and it must follow the repo's Java conventions — modern Java (records, sealed types, pattern matching, switch expressions), Optional discipline, immutability, Spring Boot constructor injection, and JUnit 5 + Mockito tests. Invoke for "add this in Java", "fix the Java build"…
python-conventions
Use when a ticket adds or changes Python code and it must follow the repo's Python conventions — PEP 8, full type hints, dataclasses, pythonic idioms, explicit error handling, and pytest with coverage. Invoke for "add this in Python", "fix the type/lint errors", "add the FastAPI/Django endpoint", or as the language…
add-integration-test
Use when a ticket asks for integration or end-to-end coverage across components — an API route hitting a database, a service-to-service call, a multi-step flow — rather than a single unit. Invoke for "test the endpoint end to end", "cover the checkout flow", or "verify the migration + query together".
add-unit-test
Use when a ticket asks for new unit tests, or when an acceptance criterion requires test coverage for a function/module/component and none exists. Invoke for "add tests for X", "cover the Y edge case", or raising coverage on a specific unit.