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 datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill verification-loop-constructiongit clone --depth 1 https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_ConstructionWrote 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/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/verification-loop-construction)<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/verification-loop-construction"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/verification-loop-construction/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/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/verification-loop-construction"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/verification-loop-construction.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 | $0.00032 | $0.03060 |
| Opus 5 | $0.00016 | $0.01530 |
| Sonnet 5 | $0.00006 | $0.00612 |
| Haiku 4.5 | $0.00003 | $0.00306 |
Grade A, and why
verification-loop-construction 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- verification-loop-construction — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Loop for Construction Automation
A systematic verification framework ensuring quality of construction automation outputs before delivery or deployment.
When to Use
Invoke this skill:
- After generating cost estimates
- After creating or updating schedules
- After processing BIM/CAD data
- After generating reports (daily, weekly, monthly)
- After running data pipelines
- Before submitting documents to clients
- Before deploying automation workflows
Verification Phases
Phase 1: Data Integrity Check
def verify_data_integrity(output: dict) -> VerificationResult:
"""Check data completeness and consistency"""
checks = []
# Completeness check
required_fields = get_required_fields(output['type'])
missing = [f for f in required_fields if f not in output]
checks.append({
'name': 'Completeness',
'status': 'PASS' if not missing else 'FAIL',
'details': f'Missing fields: {missing}' if missing else 'All required fields present'
})
# Consistency check
inconsistencies = find_inconsistencies(output)
checks.append({
'name': 'Consistency',
'status': 'PASS' if not inconsistencies else 'WARN',
'details': inconsistencies or 'No inconsistencies found'
})
# Referential integrity
broken_refs = check_references(output)
checks.append({
'name': 'Referential Integrity',
'status': 'PASS' if not broken_refs else 'FAIL',
'details': f'Broken references: {broken_refs}' if broken_refs else 'All references valid'
})
return VerificationResult(checks)
Data Integrity Checklist
- All required fields populated
- No duplicate records
- Foreign keys resolve correctly
- Date formats consistent
- Currency values formatted correctly
- Units of measure standardized
Phase 2: Business Logic Verification
def verify_business_logic(output: dict) -> VerificationResult:
"""Verify construction-specific business rules"""
checks = []
# Cost estimate checks
if output['type'] == 'cost_estimate':
# Verify totals match line items
calculated_total = sum(item['amount'] for item in output['line_items'])
declared_total = output['total']
variance = abs(calculated_total - declared_total)
checks.append({
'name': 'Total Accuracy',
'status': 'PASS' if variance < 0.01 else 'FAIL',
'details': f'Calculated: {calculated_total}, Declared: {declared_total}'
})
# Verify markup applied correctly
for item in output['line_items']:
expected_markup = item['base_cost'] * (1 + item['markup_rate'])
if abs(item['amount'] - expected_markup) > 0.01:
checks.append({
'name': f'Markup Check - {item["id"]}',
'status': 'FAIL',
'details': f'Expected: {expected_markup}, Got: {item["amount"]}'
})
# Schedule checks
if output['type'] == 'schedule':
# Verify dependencies
for task in output['tasks']:
for pred_id in task.get('predecessors', []):
pred = find_task(output['tasks'], pred_id)
if pred and pred['end_date'] > task['start_date']:
checks.append({
'name': f'Dependency Violation - {task["id"]}',
'status': 'FAIL',
'details': f'Task starts before predecessor {pred_id} ends'
})
# Verify resource allocation
resource_conflicts = find_resource_conflicts(output['tasks'])
checks.append({
'name': 'Resource Conflicts',
'status': 'PASS' if not resource_conflicts else 'WARN',
'details': resource_conflicts or 'No resource conflicts'
})
return VerificationResult(checks)
What ships with it
2 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 · 437 lines · 32 tokens per session scan A e1813ea750c4
verification-loop-construction is a skill published in the GitHub repository datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction (312 stars, last pushed 21d ago), licensed MIT. It adds 32 tokens to every session and 3,060 once invoked, about $0.0002 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
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
investigate
Investigate bugs and errors in Elixir/Phoenix — root-cause analysis for crashes, exceptions, stack traces, test failures. Use --parallel for deep 4-track investigation.
narrow-bare-rescue
Narrow bare rescue in Elixir so real errors like KeyError and typos propagate instead of being swallowed. Use to audit rescues and refactor error handling.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
verify
Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.
phx-investigate
Investigate Elixir/Phoenix bugs root-cause first. Reproduce failures, cite evidence, and use optional Amp subagents only when useful.