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 zhuangguangdahyh-dotcom/content-ops-studio --skill image-set-productiongit clone --depth 1 https://github.com/zhuangguangdahyh-dotcom/content-ops-studioWrote 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/zhuangguangdahyh-dotcom/content-ops-studio/image-set-production)<a href="https://agentmods.dev/skills/zhuangguangdahyh-dotcom/content-ops-studio/image-set-production"><img src="https://agentmods.dev/badge/skills/zhuangguangdahyh-dotcom/content-ops-studio/image-set-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/zhuangguangdahyh-dotcom/content-ops-studio/image-set-production"><img src="https://agentmods.dev/badge/skills/zhuangguangdahyh-dotcom/content-ops-studio/image-set-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 | $0.00051 | $0.01911 |
| Opus 5 | $0.00026 | $0.00955 |
| Sonnet 5 | $0.00010 | $0.00382 |
| Haiku 4.5 | $0.00005 | $0.00191 |
Grade A, and why
image-set-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 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Turn G3-approved copy and an executable Visual Plan into traceable visual assets without changing copy, inventing evidence, hiding provenance, or bypassing Operator approvals.
Required preflight
Load Image Production Context, exact Content/Copy/Cover Copy/Visual versions, Project Profile, Subject, Audience, Platform Pack, Industry Visual Pack and overlays, Project Visual Profile, confirmed global preferences, current Painpoint and Content Package, account goal, cover objective and conversion strategy, page roles, current Operator request, authorized Project/evidence assets, approved/rejected references, G4/G5 history, Feedback Events, Confirmed Rules, current Style Lock, Host ImageGen/Renderer capabilities, constraints and saved attempts. Never infer project state from chat.
Workflow
Use the bundled content-ops MCP tools for context, routing, local artifacts, quality, feedback and rules. First synthesize a Dynamic Visual Strategy for this content. Visual Mode is a primitive and Industry Pack is a prior/risk boundary; neither is a finished style. Current explicit Operator requirements outrank compatible Profile defaults. Per-content semantics, page role, evidence need and authorized assets make the final route.
COLD_START plans two or three materially different directions; LEARNING plans one or two; compatible MATURE Profiles default to one formal first-page direction; REVIEW_REQUIRED blocks reuse and requests review. Candidate directions are dynamically derived and may share a channel when their subjects, compositions and visual arguments are materially different. Never reserve A/B/C for AI, Pure Typography and Mixed templates.
Read references/universal-visual-baseline-policy.md. When no higher-precedence typography or composition rule exists, apply UVDPV-1 and TDPV-1 as fallback only. Verify the actual font and weight in the Renderer; never synthesize bold, download a font or silently fall back to PingFang. Important images need at least two real spatial relationships. Every image declares its semantic responsibility and image-text anchor. Before Visual Quality scoring, require actual-geometry and actual-pixel TYPOGRAPHY_SPATIAL_INTEGRITY plus relative TYPOGRAPHIC_BREATHING_ROOM; a score cannot override either block. Two- or three-direction sets must pass Candidate Set Visual Diversity at 85 or higher with zero hard blocks.
What ships with it
21 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.
- agents/openai.yaml 655 B
- references/asset-routing-policy.md 411 B
- references/contract.md 416 B
- references/cover-conversion-and-semantic-policy.md 1.7 KB
- references/direction-selection-policy.md 1.1 KB
- references/dynamic-visual-strategy-policy.md 2.0 KB
- references/editorial-design-knowledge-v1.md 1.6 KB
- references/examples.md 397 B
- references/failure-handling.md 1.5 KB
- references/feedback-learning-policy.md 792 B
- references/g4-style-lock-policy.md 367 B
- references/group-consistency-policy.md 1.5 KB
- references/host-imagegen-policy.md 464 B
- references/image-quality-policy.md 1.4 KB
- references/industry-visual-pack-policy.md 1.1 KB
- references/quantity-and-batch-policy.md 804 B
- references/README.md 1.4 KB
- references/set-narrative-continuity-policy.md 4.2 KB
- references/text-renderer-policy.md 2.3 KB
- references/universal-visual-baseline-policy.md 2.8 KB
- references/workflow.md 2.1 KB
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 · 57 lines · 51 tokens per session scan A 6e891b600cff
image-set-production is a skill published in the GitHub repository zhuangguangdahyh-dotcom/content-ops-studio (0 stars, last pushed 15d ago), licensed MIT. It adds 51 tokens to every session and 1,911 once invoked, about $0.0003 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
article-illustrations
Generate hand-drawn 16:9 article illustrations with the Grav character IP, sparse annotations, and absurd but clear visual metaphors.
gpt-image
Generate or edit images with GPT Image 2 or 2.5 through the packaged CLI and Reference Gallery. Use for image requests including imprecise 'GPT 2.5' model names, posters, typography, reference edits, and inpainting; resolve the model choice before generation.
get-prompt-from-image
Analyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts. Use when the user asks to recreate, imitate, reverse-engineer, or extract prompts from photographs, illustrations, 3D renders, products, characters, landscapes, typography, logos, posters, or other visual references.…
ppt-designer
A guide for planning and designing PowerPoint presentations. It covers slide structure, layouts, visual choices, animation suggestions, and speaker notes.
image-compress
A local tool for shrinking images, changing their dimensions, and converting between JPG, PNG, and WebP formats. It can process one image or all matching images in a folder.
ima2
Use the ima2-gen CLI/server to generate, edit, inspect, and manage local AI image generation jobs.