monte-carlo-data/mc-agent-toolkit / skills/prevent
monte-carlo-prevent
VerifiedShift-left safety net for dbt/SQL model edits. Runs change impact assessment before edits, generates SQL validation queries after, and executes them via `/mc-validate run`. Delegates health and monitor creation to peer skills.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 8.3 KB |
| SKILL.md | skill md | 19.0 KB |
| references/TROUBLESHOOTING.md | markdown | 1.5 KB |
| references/parameters.md | markdown | 1.0 KB |
| references/workflows.md | markdown | 36.6 KB |
| scripts/sandbox/classify_sandbox.py | script | 1.5 KB |
| scripts/sandbox/detect_hardcoded_db.py | script | 1.2 KB |
| scripts/sandbox/parse_profiles.py | script | 3.3 KB |
| scripts/sandbox/readonly_check.py | script | 2.3 KB |
| scripts/sandbox/substitute_placeholders.py | script | 3.7 KB |
| scripts/sandbox/tests/conftest.py | script | 256 B |
| scripts/sandbox/tests/test_classify_sandbox.py | script | 1.1 KB |
| scripts/sandbox/tests/test_detect_hardcoded_db.py | script | 1.6 KB |
| scripts/sandbox/tests/test_integration_smoke.py | script | 2.8 KB |
| scripts/sandbox/tests/test_parse_profiles.py | script | 3.1 KB |
| scripts/sandbox/tests/test_readonly_check.py | script | 3.9 KB |
| scripts/sandbox/tests/test_substitute_placeholders.py | script | 3.7 KB |
scripts/sandbox/tests/test_integration_smoke.py
View on GitHub"""End-to-end smoke: simulate the Workflow 4.1/4.2 script chain on the happy path."""
import json
import subprocess
import sys
from pathlib import Path
SANDBOX_DIR = Path(__file__).resolve().parents[1]
PROFILES = """
default:
target: prod
outputs:
prod:
type: snowflake
database: personal_alice
schema: prod
role: DATA_ANALYST
warehouse: research
account: dka87615.us-east-1
"""
MODEL_SQL = """\
{{ config(materialized='table', schema='prod') }}
SELECT 1 AS account_id
"""
VALIDATION_SQL = """\
-- validation queries
SELECT 'dev' AS src FROM <YOUR_DEV_DATABASE>.prod.client_hub
UNION ALL
SELECT 'prod' AS src FROM analytics.prod.client_hub
WHERE <YOUR_DEV_DATABASE>.prod.client_hub.account_id IS NOT NULL;
"""
def _run(script: str, *args) -> tuple[int, str, str]:
out = subprocess.run(
[sys.executable, str(SANDBOX_DIR / script), *args],
capture_output=True, text=True,
)
return out.returncode, out.stdout, out.stderr
def test_happy_path(tmp_path):
profiles = tmp_path / "profiles.yml"
profiles.write_text(PROFILES)
model = tmp_path / "client_hub.sql"
model.write_text(MODEL_SQL)
sql = tmp_path / "client_hub_20260423.sql"
sql.write_text(VALIDATION_SQL)
# 1. Parse profiles.
code, out, err = _run("parse_profiles.py", str(profiles))
assert code == 0, err
profile_info = json.loads(out)
assert profile_info["database"] == "personal_alice"
# 2. Classify.
code, out, _ = _run("classify_sandbox.py", profile_info["database"])
assert code == 0
assert json.loads(out)["classification"] == "personal"
# 3. No hard-coded database in the model.
code, out, _ = _run("detect_hardcoded_db.py", str(model))
assert code == 0
assert json.loads(out)["database"] is None
# 4. Substitute placeholders. Default output lives in validation/run/.
code, out, _ = _run("substitute_placeholders.py", str(sql), "--dev-db", "personal_alice")
assert code == 0
sub_info = json.loads(out)
assert sub_info["replaced_count"] == 2
assert "analytics" in sub_info["literal_databases"]
from pathlib import Path as _P
assert _P(sub_info["output_path"]).parent == sql.parent / "run"
# 5. Read-only check on the substituted output.
code, out, _ = _run("readonly_check.py", sub_info["output_path"])
assert code == 0
assert json.loads(out)["ok"] is True
def test_prod_classification_gets_flagged(tmp_path):
# Engineer's profile is mis-pointed at real prod.
profiles = tmp_path / "profiles.yml"
profiles.write_text(PROFILES.replace("personal_alice", "ANALYTICS"))
code, out, _ = _run("parse_profiles.py", str(profiles))
assert code == 0
db = json.loads(out)["database"]
code, out, _ = _run("classify_sandbox.py", db)
assert json.loads(out)["classification"] == "prod"
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |