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 ai-act-compliancegit 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/ai-act-compliance)<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/ai-act-compliance"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/ai-act-compliance/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/ai-act-compliance"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/ai-act-compliance.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 | $0.00052 | $0.00598 |
| Opus 5 | $0.00026 | $0.00299 |
| Sonnet 5 | $0.00010 | $0.00120 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
ai-act-compliance 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EU AI Act Compliance for Construction AI (2026)
Why it matters
The EU AI Act (2024/1689) is binding from 2025–2027 in phases. Construction AI — estimators, computer-vision site monitoring, agent assistants — mostly lands in limited or minimal risk, but misclassification or missing transparency is a compliance failure, and high-risk uses (safety-critical, worker monitoring, access decisions) bring real obligations.
Classification quick check for construction tools
| System | Likely tier | Obligations |
|---|---|---|
| Cost estimation assistant (BOQ, unit prices) | limited / minimal | transparency (users know it is AI), basic logging |
| Schedule optimisation | minimal | none beyond general law |
| Site camera CV for progress | limited | transparency, data minimisation |
| CV for PPE/safety enforcement | high risk (safety component?) | full: risk management, data governance, human oversight, logs |
| Worker performance monitoring | high risk (employment) | prohibited or high-risk — treat carefully |
| AI agent that signs/submits binding documents | not allowed without human | human oversight mandatory |
Rule of thumb: if a human previously had to sign it, an AI must not sign it alone.
Practical compliance checklist (per tool)
- Classify — document the risk tier and reasoning.
- Transparency — users must know they interact with AI output; mark AI-generated estimates as such.
- Human oversight — a qualified human reviews binding estimates, contracts, safety decisions.
- Data governance — minimal personal data in site CV; no biometric identification.
- Logging — record model, inputs, outputs, version (the ERP usage-ledger pattern).
- Instructions for use — document limitations (e.g. early estimates ±30–50%).
Mapping to the DDC stack
oce-estimate-boq,cost-estimation-*,cost-prediction: limited risk — add AI-output labels.progress-monitoring-cv,defect-detection-ai: limited — no personal data, transparency.safety-compliance-checkerenforcing PPE via CV: reclassify — keep a human in the loop, document.ai-agent-orchestration: supervisor must be a human at decision gates.
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 · 45 lines · 52 tokens per session scan A 58a557250d57
ai-act-compliance 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 52 tokens to every session and 598 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 2026-09-03.
Other skills, from other repositories
compliance-audit
Audits codebases against compliance frameworks (SOC2, HIPAA, PCI-DSS, GDPR, ISO27001, etc.) using parallel agents per subdirectory/sub-repo. Produces a detailed markdown report with line-level code references. Use when you need to check a directory or monorepo for compliance violations before an audit or review.
legal-discovery
Audit e-discovery and litigation document review systems -- data collection pipelines (PST, MBOX, SharePoint, Slack), document processing (OCR via Tesseract/ABBYY, metadata extraction, deduplication), Technology Assisted Review (TAR 1.0/2.0/CAL with recall/precision tracking).
litigation-predictor
Audit litigation analytics and case outcome prediction systems -- ML outcome models (logistic regression, gradient boosting, neural nets with temporal train/test splits), settlement range modeling (Monte Carlo simulation, comparable case matching, BATNA analysis).
sales-readiness
Audit whether a product is ready for enterprise sales. Use when you need to assess SSO/SAML/SCIM support, RBAC maturity, multi-tenancy data isolation, audit logging coverage, public API quality, SLA operational readiness, SOC2/ISO27001 certification gaps, GDPR data residency controls.
audit-support
Analyzes audit readiness systems for internal control testing, evidence collection workflows, statistical sampling methodology, audit finding documentation, and remediation tracking using PCAOB, ISA, and SOX compliance frameworks..
case-outcome-predictor
Audit legal case prediction systems for bias, fairness, accuracy, and ethical guardrails. Use when: 'check my prediction model for bias', 'audit case outcome fairness', 'evaluate legal ML model', 'review sentencing prediction ethics', 'analyze bail risk algorithm', 'fairness metrics for justice system AI'.