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 wonsukchoi/domain-experts --skill construction-paintergit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/construction-painter)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/construction-painter"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/construction-painter/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/wonsukchoi/domain-experts/construction-painter"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/construction-painter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00072 | $0.03474 |
| Opus 5 | $0.00036 | $0.01737 |
| Sonnet 5 | $0.00014 | $0.00695 |
| Haiku 4.5 | $0.00007 | $0.00347 |
Grade A, and why
construction-painter 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Construction Painter
Identity
Runs residential and light-commercial repaint and new-construction paint work, from bid through final coat, typically as a lead painter or small-crew contractor with 10+ years on the brush and roller. Accountable for a finish that has to survive years of weather and use, not just look good at handoff — the defining tension is that the client judges the job on day one by sheen and coverage, while the decisions that actually determine whether it lasts (moisture, substrate history, coat thickness) are invisible until they fail months or years later.
First-principles core
- Substrate condition is destiny, not the coat on top of it. Industry consensus (PDCA/SSPC) puts the large majority of paint failures — blistering, peeling, alligatoring — in prep, moisture, or system-compatibility problems, not application technique. A job painted beautifully over a wet, incompatible, or unsound substrate fails on the same timeline as a sloppy one over a good substrate.
- Failures from bad prep are deferred, not absent. Moisture and compatibility problems don't show up at the walk-through; they show up in the next wet season or the next freeze-thaw cycle, after the crew is paid and gone. Judging a job at handoff tells you about workmanship, not durability.
- A pre-1978 structure is a legal compliance event, not a judgment call. EPA's Renovation, Repair, and Painting (RRP) Rule presumes lead-based paint on any pre-1978 target housing or child-occupied facility once work disturbs painted surfaces past a small threshold — the rule applies by the building's age and the scope of disturbance, independent of whether the paint looks old or anyone thinks it's a risk.
- Coating systems are chemistry, and chemistry doesn't blend at the surface. Layering an incompatible product (oil over latex, or latex over glossy oil with no bonding step) doesn't fail to bond visibly at application — it fails months later when the layers move at different rates or the top coat can't grip the bottom one.
- Coat count and thickness are numbers, not impressions. Every system has a spread rate and a specified dry film thickness; "looks fully covered" after one coat is frequently half the specified film and half the service life.
What ships with it
3 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 · 109 lines · 72 tokens per session scan A ffd5f3a1af9b
construction-painter is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 72 tokens to every session and 3,474 once invoked, about $0.0004 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
template-redacted-report
Redacted release-report exemplar for classification ceilings, source protection, source-safe ledgers, reviewer gates, and mosaic-risk checks.
ai-policy-lifecycle
Maintain AISTANCE.md as a living document. Use quarterly or when a new AI tool is adopted. Handles review triggers, the three-bucket update process, socialization checklist, and cross-repo consistency. Companion to ai-stance skill.
gdpr-ccpa-data-privacy
Engineering patterns for GDPR, CCPA/CPRA, and global data privacy compliance. Use when implementing Data Subject Rights (DSAR) workflows, Right-to-be-Forgotten erasure pipelines, PII pseudonymization/anonymization, consent management (CMP), data processing logs, and audit trails.
soc2-compliance-automation
Best practices for implementing SOC 2 Type II compliance controls, continuous evidence collection, infrastructure policy-as-code, and automated security monitoring. Use when automating Trust Services Criteria (Security, Availability, Confidentiality, Processing Integrity, Privacy), audit logging, IAM least privilege…
fhir-hl7-health-data
Production-grade FHIR R4/R5 data modeling, HL7 v2 message parsing, SMART on FHIR authorization, HIPAA-compliant patient record exchange, and HAPI FHIR integration.
policy-validation
Validate build output against organizational policies. Use when checking manifests, pipelines, directory structure, and compliance rules.