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-value-studiesgit 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-value-studies)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-value-studies"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-value-studies.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.01122 |
| Opus 5 | $0.00012 | $0.00561 |
| Sonnet 5 | $0.00005 | $0.00224 |
| Haiku 4.5 | $0.00002 | $0.00112 |
Grade A, and why
apply-value-studies 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 7d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Value Studies
Plan the light-and-dark structure of a composition before applying color, establishing a value map that governs the entire work.
Why This Is Best Practice
Adopted by: The atelier tradition (R.H. Ives Gammell, Nelson Shanks, Juliette Aristides); realist painting programs at the Florence Academy of Art, Grand Central Atelier, and Watts Atelier; used by James Gurney in his Dinotopia concept workflow and by Richard Schmid as the foundation of alla prima direct painting Impact: Painters who complete value studies before color work report 50–70% fewer major compositional revisions after the underpainting stage; Gurney documents that concept illustration approval rates double when value thumbnails are submitted before color comps Why best: The human visual system is more sensitive to value contrast than to hue contrast — value structure determines readability, focal hierarchy, and spatial depth; color applied over a flawed value structure cannot fix the underlying failures
Sources: James Gurney "Color and Light: A Guide for the Realist Painter" (2010); Richard Schmid "Alla Prima: Everything I Know About Painting" (1998); Juliette Aristides "Classical Painting Atelier" (2008)
Steps
- Create thumbnail-scale value sketches first — work at 3–5 cm scale so detail is impossible and only large value masses remain; produce five to ten thumbnails exploring different light directions and value arrangements before committing to one.
- Limit to three to five value steps — reduce the world to a shadow mass, a midtone mass, a light mass, and optionally a highlight and a deep accent; more steps at the planning stage adds complexity without structural insight.
- Squint at the subject — squinting optically blurs detail and reveals the underlying value masses; practice until you can identify the dominant light, midtone, and shadow regions instantly.
- Establish the value key — decide whether the composition will be high key (mostly lights), low key (mostly darks), or full range; every individual value decision must serve the key.
- Design the focal point as the highest contrast — place the greatest value difference (dark against light) at the intended focal point; this is the single most powerful tool for directing viewer attention.
- Unify the shadow mass — all shadows in a natural lighting scenario share a common value family; keep them within two value steps of each other to prevent the composition from fracturing into unrelated pieces.
- Separate light and shadow edges clearly — at the terminator (the boundary between light and shadow), the value change must be decisive; a gradual, blurry terminator reads as weak, indirect light regardless of the scene's intended light source.
- Check the study at arm's length — hold the value sketch at reading distance and verify that the focal hierarchy reads immediately; if the eye does not know where to look in three seconds, the value structure needs revision.
- Transfer the value map to the canvas — block in the composition with a monochromatic underpainting (raw umber, ivory black) matching the value study before introducing any color.
- Maintain value integrity when adding color — use a handheld value scale (a Notan card or printed gray scale) to check that each color applied matches its intended value step; color temperature shifts perception of value.
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.
- 7d ago First seen · 53 lines · 24 tokens per session scan A a0b2de4bcf92
apply-value-studies is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 19d ago), licensed MIT. It adds 24 tokens to every session and 1,122 once invoked, about $0.0001 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.
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.