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-watercolor-techniquegit 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-watercolor-technique)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-watercolor-technique"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-watercolor-technique/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-watercolor-technique"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-watercolor-technique.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 | $0.00044 | $0.01482 |
| Opus 5 | $0.00022 | $0.00741 |
| Sonnet 5 | $0.00009 | $0.00296 |
| Haiku 4.5 | $0.00004 | $0.00148 |
Grade A, and why
apply-watercolor-technique 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 11d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Watercolor Technique
Produce luminous watercolor paintings by controlling pigment-to-water ratio, choosing wet-on-wet vs wet-on-dry deliberately, preserving whites from the start, and building glazed layers from light to dark.
Why This Is Best Practice
Adopted by: John Singer Sargent's watercolors (now in major museum collections worldwide) exemplify the wet-on-wet/wet-on-dry control that watercolor mastery requires. The Royal Watercolour Society and American Watercolor Society both define luminosity and transparency as the defining qualities of high watercolor. All professional watercolor instruction (National Watercolor Society workshops, Bockingford and Winsor & Newton educational materials) centers on water-to-pigment ratio control as the primary technical skill. Why best: Watercolor is unforgiving of rework — pigment can't be added as opaque white and dried layers can't be lifted without disturbing the surface, so the sequence (whites preserved first, light-to-dark glazing, deliberate wet-on-wet vs wet-on-dry choice) is the only path to luminous results rather than mud. Impact: The most common failure mode in watercolor is overworking — re-wetting dried layers disturbs the surface, lifts pigment, and creates muddy color. A painter who plans the light-to-dark sequence and preserves whites from the beginning avoids these failures entirely. Wet-on-wet produces the soft, atmospheric edges unique to watercolor; wet-on-dry produces the crisp, controlled edges that give definition. Using both intentionally produces paintings that neither oil nor digital can replicate.
Steps
1. Plan the painting before touching water — map whites
Watercolor is subtractive only: you cannot add white pigment and maintain transparency. All lights and whites must be preserved as unpainted paper.
Before mixing:
- Sketch lightly in pencil (HB or lighter — harder graphite stays visible and bleeds less)
- Map every light shape: sky holes in foliage, highlights on water, light on faces
- Decide: which whites are absolute (paper preserved) vs which will be lightened glazes
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.
- 11d ago First seen · 98 lines · 44 tokens per session scan A 0b53afbcff6d
apply-watercolor-technique is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 22d ago), licensed MIT. It adds 44 tokens to every session and 1,482 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
creative-writing
Patterns for fiction, narrative structure, character development, dialogue, and storytelling craft.
presenting-conference-talks
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.
yt-dlp-downloader
Generate and run yt-dlp download commands with probe-driven format selection, safe output naming, retry defaults, and structured execution reports. Use when users want to download videos, extract audio, fetch playlists, grab subtitles, handle authenticated/age-gated content, or download live streams. Covers single…
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.