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 agentmods add skills/alfredxw/denova/interactive-imagenpx skills add alfredxw/denova --skill interactive-imagegit clone --depth 1 https://github.com/alfredxw/denovaWrote 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/alfredxw/denova/interactive-image)<a href="https://agentmods.dev/skills/alfredxw/denova/interactive-image"><img src="https://agentmods.dev/badge/skills/alfredxw/denova/interactive-image.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 | $0.00014 | $0.00343 |
| Opus 5 | $0.00007 | $0.00171 |
| Sonnet 5 | $0.00003 | $0.00069 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
interactive-image 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 5d 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.
What it actually says
Interactive Image
Use this Skill when the caller's purpose is interactive_image.
Workflow
- Build the image prompt only from interactive-story events already established in
source_context. - Choose the most visually compelling moment that best represents the current turn. Do not reveal future plot, hidden identities, or undisclosed canon.
- If the caller provides an image preset, incorporate it as the visual direction for the image prompt.
- Write a complete Chinese image prompt containing the subject, scene, composition, lighting, mood, and visual style, with explicit negative constraints against text, watermarks, and logos.
- Call
generate_imagewith:purpose:interactive_image.story_id,branch_id, andturn_id: copy the caller-provided values exactly.prompt: the complete Chinese image prompt.alt_text: use the caller-provided value, or write a short Chinese description when it is absent.size: optionally choose a supported 2K, 3K, or 4K size based on the composition; otherwise omit it.output_format:pngorjpeg; omit it when uncertain.
- After the tool returns, report the generation result briefly and do not advance the story.
Constraints
- Generate exactly one interactive image per request.
- Do not generate batches of candidates.
- Do not modify story prose, chapters, lore, or configuration.
- Do not insert image Markdown into narrative text.
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.
- 5d ago First seen · 33 lines · 14 tokens per session scan A aff3170b6adc
interactive-image is a skill published in the GitHub repository alfredxw/denova (690 stars, last pushed yesterday), licensed Apache-2.0. It adds 14 tokens to every session and 343 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 2026-08-30.
Other skills, from other repositories
llmlint
A Chinese-prose rule library with two entry points. Before writing, emit the rules as writing constraints to load into a system prompt or style guide. After writing, lint the draft with static rule hits, neural AIGC heatmaps, contextual review, approved repair, and local learning notes. Use when drafting or rewriting…
profile-system-guide
Guide users and agents through Neuro Book harness, TSX profiles, ProfileTurnPlan, skills, user-assets overlays, settings forms, profile home resources, profile compile checks, templates, system restore, and safe profile editing.
diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
novel-technique-character-card-workshop
重量级角色写卡、人物塑造、人设整理与角色理解流程。用于用户要从模糊角色印象、萌点、标签、OC、人设草稿或角色卡想法整理成可写角色，进行 20/24/80/200 问循环问答，设计或校验基础信息、调色盘、三面性、混色、核心人格层、二次解释、意象，或防止 AI 把角色写成标签化人设；适合作为 novel-setup 角色设计阶段的深挖前置或参考技法。用户明确要求批量出候选答案再逐题挑选时，可走可选的批量候选模式。.
novel-writer-execution
Writer 执行手册：收到 brief 后的详细执行流程、决策点、常见陷阱。Writer profile 内部参考，不由 leader 直接调用。.