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 content-finalizationgit 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/content-finalization)<a href="https://agentmods.dev/skills/zhuangguangdahyh-dotcom/content-ops-studio/content-finalization"><img src="https://agentmods.dev/badge/skills/zhuangguangdahyh-dotcom/content-ops-studio/content-finalization/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/content-finalization"><img src="https://agentmods.dev/badge/skills/zhuangguangdahyh-dotcom/content-ops-studio/content-finalization.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 | $0.00037 | $0.00712 |
| Opus 5 | $0.00018 | $0.00356 |
| Sonnet 5 | $0.00007 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
content-finalization 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Validate the complete content/image set, request final review, archive a G5-approved version, and synchronize owned final fields with read-back verification.
Image Production V1 is frozen. Finalization never changes Copy or Visual artifacts and never calls Renderer or ImageGen.
Use this skill when
All required pages exist and need QA, G5 preparation, approved archiving, synchronization, or partial-sync repair.
Do not use this skill when
Images are incomplete, QA is failing without a repair request, or G5 is absent for finalization.
Required preflight
Verify versions, required artifacts, hashes, image states, QA capability, G5 where required, workspace/asset capabilities, unique keys, locks, and prior sync log.
Inputs
Task envelope, content and visual versions, image manifest, render/QA reports, approval event, workspace state, and sync history.
Workflow boundary
Run content, visual, file, and data QA; request G5; after version-matched checksum-bound approval execute LOAD_FINALIZATION_CONTEXT → VERIFY_APPROVAL_CHAIN → VERIFY_FINAL_ASSETS → VERIFY_GROUP_EVIDENCE → BUILD_FINAL_MANIFEST → BUILD_FINAL_SET_FINGERPRINT → SANITIZE_FINAL_PNG_METADATA → BUILD_DELIVERY_PACKAGE → VERIFY_DELIVERY → WRITE_ARCHIVE_STATE. Workspace metadata synchronization and Operator-directory export are separate explicit actions. Retry only failed side effects.
Human approval boundary
Never finalize before explicit G5. Only the Router writes the approval event.
Allowed writes
Immutable Final Manifests, Final Set Fingerprints, approved-only sanitized Delivery Packages, PNG Metadata Sanitization Reports, Delivery Integrity Reports, archive states and synchronization logs through Adapters. With explicit confirmation, copy sanitized final pages to a managed leaf below an Operator-specified absolute directory. Attachment upload remains an independent capability and may be deferred.
Forbidden actions
Finalizing failed QA; submitting without G5; fabricating attachment success; simple blind increments of painpoint content counts; destructive rollback.
What ships with it
2 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.
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 · 63 lines · 37 tokens per session scan A b5d5a379713b
content-finalization is a skill published in the GitHub repository zhuangguangdahyh-dotcom/content-ops-studio (0 stars, last pushed 15d ago), licensed MIT. It adds 37 tokens to every session and 712 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
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.