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 bobmatnyc/claude-mpm-skills --skill test-quality-inspectorgit clone --depth 1 https://github.com/bobmatnyc/claude-mpm-skillsWrote 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/bobmatnyc/claude-mpm-skills/test-quality-inspector)<a href="https://agentmods.dev/skills/bobmatnyc/claude-mpm-skills/test-quality-inspector"><img src="https://agentmods.dev/badge/skills/bobmatnyc/claude-mpm-skills/test-quality-inspector/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bobmatnyc/claude-mpm-skills/test-quality-inspector"><img src="https://agentmods.dev/badge/skills/bobmatnyc/claude-mpm-skills/test-quality-inspector.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00021 | $0.02997 |
| Opus 5 | $0.00010 | $0.01499 |
| Sonnet 5 | $0.00004 | $0.00599 |
| Haiku 4.5 | $0.00002 | $0.00300 |
Grade A, and why
test-quality-inspector 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 9d 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 — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Example Test Inspection Report
Scenario: User Registration Feature
Engineer's Test Suite
# test_user_registration.py
def test_user_creation():
"""Test user creation"""
user = create_user("[email protected]", "password123")
assert user
def test_login():
"""Test login"""
user = create_user("[email protected]", "password123")
result = login("[email protected]", "password123")
assert result
def test_duplicate_email():
"""Test duplicate email"""
create_user("[email protected]", "password123")
user2 = create_user("[email protected]", "password456")
assert user2
QA Inspection Report
Test 1: test_user_creation()
Claimed Intent: Test user creation Actually Tests: Object instantiation only
Issues Found
🔴 CRITICAL: Worthless Assertion
assert user # Line 5
- Would pass with corrupt data
- Would pass with wrong email
- Would pass with invalid password hash
- Would pass if database save failed
Mental Debug: User object with garbage data would pass this test.
🟠 HIGH: Missing Validation Tests
- No test for invalid email format
- No test for weak password
- No test for duplicate email (separate test exists but broken)
- No test for SQL injection in email
🟠 HIGH: No Persistence Verification
- Test doesn't verify user is saved to database
- Test doesn't verify user can be retrieved
- Transaction might be rolled back
🟡 MEDIUM: Vague Test Name
- "test_user_creation" doesn't describe what should happen
- Better: "test_user_creation_with_valid_data_persists_to_database"
Suggested Improvements
def test_user_creation_with_valid_data_persists_to_database():
"""Creating a user with valid email and password should:
1. Create user object with correct attributes
2. Save to database
3. Hash password (not store plaintext)
4. Set default role and active status
"""
email = "[email protected]"
password = "SecurePass123!"
user = create_user(email, password)
# Verify user object
assert user.id is not None, "User should have an ID after creation"
assert user.email == email, "Email should match input"
assert user.is_active is True, "New users should be active by default"
assert user.role == "user", "New users should have 'user' role"
assert user.created_at is not None, "Created timestamp should be set"
# Verify password is hashed, not plaintext
assert user.password_hash != password, "Password should be hashed"
assert len(user.password_hash) > 50, "Password hash should be substantial"
# Verify persistence
retrieved_user = User.get_by_email(email)
assert retrieved_user is not None, "User should be retrievable from database"
assert retrieved_user.id == user.id, "Retrieved user should match created user"
def test_user_creation_with_invalid_email_format_raises_validation_error():
"""Creating a user with malformed email should raise ValidationError"""
invalid_emails = [
"not-an-email",
"@example.com",
"test@",
"test [email protected]",
"",
]
for invalid_email in invalid_emails:
with pytest.raises(ValidationError) as exc:
create_user(invalid_email, "password123")
assert "email" in str(exc.value).lower()
assert "invalid" in str(exc.value).lower()
def test_user_creation_with_weak_password_raises_validation_error():
"""Creating a user with weak password should raise ValidationError"""
weak_passwords = [
"123", # Too short
"password", # No numbers
"12345678", # No letters
"", # Empty
]
for weak_password in weak_passwords:
with pytest.raises(ValidationError) as exc:
create_user("[email protected]", weak_password)
assert "password" in str(exc.value).lower()
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 427 lines · 21 tokens per session scan A 0057eeef0b2d
test-quality-inspector is a skill published in the GitHub repository bobmatnyc/claude-mpm-skills (75 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 2,997 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 2026-09-03.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.