Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/gaia-research/gaia-skill-heavennpx agentmods add skills/gaia-research/gaia-skill-heaven/lucy-image-productionWrote 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/gaia-research/gaia-skill-heaven/lucy-image-production)<a href="https://agentmods.dev/skills/gaia-research/gaia-skill-heaven/lucy-image-production"><img src="https://agentmods.dev/badge/skills/gaia-research/gaia-skill-heaven/lucy-image-production/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/gaia-research/gaia-skill-heaven/lucy-image-production"><img src="https://agentmods.dev/badge/skills/gaia-research/gaia-skill-heaven/lucy-image-production.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 | $0.00017 | $0.02586 |
| Opus 5.5 | $0.00007 | $0.01034 |
| Sonnet 5.5 | $0.00003 | $0.00517 |
| Haiku 4.5 | $0.00002 | $0.00259 |
Grade A, and why
lucy-image-production 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 1mo 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lucy Image Production
This is the Skill Heaven specialization of Gaia Image Production. It governs every generated Lucy raster, background removal, upscale, crop, filter, and WebP export in this repository.
Authority
Read these before production, in this order:
packages/site/src/assets/lucy/authority/lucy-character-sheet-master.pngdocs/lucy/authority/LUCY_CANONICAL_CHARACTER_SHEET.mddocs/lucy/authority/lucy-canon.jsonpackages/site/src/assets/lucy/authority/lucy-original-reference.jpg- The assigned job in
docs/lucy/production/ASSET_PRODUCTION_PLAN.md
The final sheet and written canon win over every earlier iteration. Lucy is one character. Her anatomy and outfit do not transform between states.
Paid generation contract
- Use
gpt-image-2only. - Make exactly one generation call for each assigned
GEN-*job. - Do not request alternates, variations, or a second attempt.
- Include the authority images in the generation context.
- Preserve the first result even when it fails a gate; mark the job blocked.
- Self-review the result once. Continue only with deterministic local processing: crop, resize, alpha extraction, cleanup, compositing, inversion, color filtering, and WebP export.
- An owner-authorized candidate brief may define multiple named candidates. Treat each named candidate or bounded edit as its own one-call job. Never add replacements beyond the explicit candidate count, and never promote a candidate before the brief's human selection gate.
Storage contract
- Raw/master/intermediate PNGs:
packages/site/assets/workbench/lucy/<job-id>/(gitignored). - As-is backup: run
scripts/assets/backup-lucy-pngs.shafter any PNG lands. - Production deliverables:
packages/site/src/assets/lucy/as WebP. - The canonical sheet and owner-approved source masters already retained under
src/assets/lucy/*/masters/may stay in Git for authority and provenance, but frontend code must never import those PNGs directly; browsers load delivery WebPs only. - Write a receipt to
docs/lucy/production/runs/<job-id>.mdwith model, prompt path or full prompt, input authorities, raw path, outputs, dimensions, alpha result, self-review results, and any blocked item.
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.
- 1mo ago First seen · 217 lines · 17 tokens per session scan A ba84cffff7a7
lucy-image-production is a skill published in the GitHub repository gaia-research/gaia-skill-heaven (4 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 2,586 once invoked, about $0.0001 per session on Opus 5.5. 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
architecture-compass
Architectural thinking partner for an existing repository — scans the codebase, conducts a structured interview, agrees on current architectural state and recommended direction, and produces a shareable insights document. Scoped to one repository, module, or folder. Does not execute transformation — it orients. Use…
skill-review
Deep behavioral audit of a Lattice skill — proposes 3 review personas relevant to the skill, runs independent scenario analysis from each persona's perspective, then merges only the high-confidence, practical findings into a severity-ordered gap report with proposed fixes. Structural validation (conventions…
architecture-refiner
Facilitate a structured conversation to define architecture principles for a repository. Supports multiple architecture styles: clean architecture (default), hexagonal / ports & adapters, modular monolith, or custom. Produces a formal architecture document that the corresponding atom will use. Use when setting up a…
clean-code-refiner
Facilitate a structured conversation to define clean code principles for a repository. Produces a formal clean-code.md document that the clean-code atom will use as its override. Use when setting up coding standards, defining code quality rules, or when the user says 'setup clean code', 'define coding standards'…
review-refiner
Facilitate a structured conversation to customize how the review molecule works -- atom loading rules, severity classification, report format, scope rules, insight capture, and health logging. Produces a formal review-standards.md document that the review molecule will use as its process configuration. Use when the…
review
Perform a structured code review by composing validation checklists from relevant atoms based on what code changed. Loads atoms conditionally -- clean-code always, architecture/DDD/security/tests only when the delta touches their domain. Produces a severity-ordered report with specific locations and fixes. Use when…