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 dasein108/slope-studio --skill story-illustratorgit clone --depth 1 https://github.com/dasein108/slope-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/dasein108/slope-studio/story-illustrator)<a href="https://agentmods.dev/skills/dasein108/slope-studio/story-illustrator"><img src="https://agentmods.dev/badge/skills/dasein108/slope-studio/story-illustrator/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/dasein108/slope-studio/story-illustrator"><img src="https://agentmods.dev/badge/skills/dasein108/slope-studio/story-illustrator.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 | $0.00067 | $0.02774 |
| Opus 5 | $0.00034 | $0.01387 |
| Sonnet 5 | $0.00013 | $0.00555 |
| Haiku 4.5 | $0.00007 | $0.00277 |
Grade A, and why
story-illustrator 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 12d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
story-illustrator — long videos from prose, with characters that keep their face
Turns finished prose (a story, an audiobook chapter) into a long illustrated video. Characters are learned once from a folder of reference images and stay visually consistent across every scene — including multi-character scenes.
Mental model
Two artifacts do all the anti-drift work; protect them:
- The character card (
characters/<name>/card.json) — a LOCKED identity descriptor + 1 canonical anchor image. The descriptor is injected verbatim into every scene prompt at render time (the storyboard LLM never sees it, so it can't paraphrase it). The SAME anchor image is sent to the image model for every scene. - The storyboard script (
01_script.json) — scenes carrycharacters: [...]tags;visual_promptholds ONLY action + setting, never a character's look.
Generation = Nano Banana edit mode (multi-image reference) for character scenes, cheap model (flux-schnell/pollinations) for scenery beats — roughly halves cost. A vision drift-gate compares each rendered character scene against the card and regenerates once with concrete corrections.
Workflow
1. Prepare characters (once per character)
Put 2–8 clear reference images in characters/<name>/ (face visible, single
subject). Then:
studio characters-build gurdjieff # card + best-ref anchor
studio characters-build gurdjieff --portrait --style "painterly 1900s oil"
--portrait renders ONE neutral master portrait (from the best reference, in the
video's art style) and makes it the sole anchor — strongest consistency; use it
whenever the character recurs across videos. Rebuild the card if the folder changes.
Check the printed descriptor: fix wrong facts by editing card.json directly
(it's yours to curate — the build is a starting point).
1b. Characters WITHOUT reference images (text-derived cards)
A story usually has characters nobody has photos of (the abbot, the sister, the stranger). Their look must still be decided ONCE and reused — otherwise the image model re-imagines them every scene and they drift. Two ways to lock them:
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.
- 12d ago First seen · 218 lines · 67 tokens per session scan A 0946c639f409
story-illustrator is a skill published in the GitHub repository dasein108/slope-studio (3 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 2,774 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
dws
A command-line guide for DingTalk, a workplace platform with chat, documents, calendars, approvals, tasks, and other business tools.
package-author
A packaging guide for turning scripts, skills, or an MCP service into a standard plugin package. MCP is a way for an AI assistant to connect to external tools.
notes
Skill "notes" from Pinvou/pinvou-agent, covering ima notes, operations, write rules, examples and response handling.
taiyi-integration
A project workflow skill for closing a TaiyiForge change and recording it in a CHANGELOG.md file. It checks review results, tests, and the state of the working tree before archiving the change.
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
taiyi-evolve
A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.