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 jeffreytse/grimoire-core --skill apply-plein-air-paintinggit clone --depth 1 https://github.com/jeffreytse/grimoire-coreWrote 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/jeffreytse/grimoire-core/apply-plein-air-painting)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-plein-air-painting"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-plein-air-painting/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/jeffreytse/grimoire-core/apply-plein-air-painting"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-plein-air-painting.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 | $0.00043 | $0.01406 |
| Opus 5 | $0.00022 | $0.00703 |
| Sonnet 5 | $0.00009 | $0.00281 |
| Haiku 4.5 | $0.00004 | $0.00141 |
Grade A, and why
apply-plein-air-painting 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 12d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Plein Air Painting
Paint on location by establishing a light-locked value structure in the first 20 minutes, then working color temperature and detail into that structure before conditions change — producing a complete study in 1–3 hours.
Why This Is Best Practice
Adopted by: Plein air painting was codified by the French Impressionists (Monet, Pissarro, Sisley) and elevated by the Barbizon school as the foundational training method for landscape painters. Plein Air Painters of America, Outdoor Painters Society, and every major representational painting program require plein air studies as core curriculum. Leading workshops (Cape Cod School of Art, Scottsdale Art School) structure entire curricula around outdoor location painting. Why best: Light and atmosphere shift continuously outdoors, so a workflow that locks the value structure first and defers detail is the only approach that reliably survives changing conditions — chasing detail before values are set guarantees a painting with mismatched light by the time it's finished. Impact: Monet's plein air studies produced his signature understanding of shifting light quality — an understanding impossible to develop from reference photos, which flatten color temperature shifts. The core discipline of plein air painting — commit to a value structure before light changes, work fast, prioritize large shapes over detail — transfers directly to studio painting speed and decision-making. Artists trained exclusively in studio often produce static, artificial light; plein air forces observation of transient atmospheric conditions.
Steps
1. Set up efficiently — target under 10 minutes
Light changes every 20–30 minutes; slow setup wastes valuable time when light quality is optimal.
Equipment:
- Pochade box or French easel
- Limited palette (see Step 2)
- Panels, not canvas (panels are rigid; wind doesn't buckle them)
- Viewfinder or value finder (red filter to check values)
Site selection:
- Find your composition before unpacking — walk 3–5 viewpoints, choose the strongest
- Position easel with back to primary light source; avoid painting into direct sun
- Set up in shade where possible (ambient light reads values more accurately than full sun in your eyes)
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.
- 12d ago First seen · 96 lines · 43 tokens per session scan A d76378ca4ec3
apply-plein-air-painting is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 24d ago), licensed MIT. It adds 43 tokens to every session and 1,406 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 2026-08-31.
Other skills, from other repositories
semantic-model-disambiguation
Analyze Power BI semantic models for column-level overlaps that confuse Copilot and Fabric data agents. Detect ambiguity, review with domain expert, apply fixes via MCP.
prompt-2-data
Generate comprehensive synthetic relational data for any specified subject with multiple normalized CSV files maintaining referential integrity.
infrastructure-as-code
Domain: DevOps & Cloud Engineering.
academic-paper-drafting
End-to-end academic paper drafting for CHI, HBR, journals, and conferences with venue-specific templates, drafting workflows, and revision strategies.
research-first-development
Build knowledge bases that build software — research before code, teach before execute.
agent-governance
Patterns for adding safety, trust, and policy enforcement to AI agent systems -- control which tools agents can call, what content they process, and maintain accountability through audit trails.