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 lincwang123-bot/moonlit-stories --skill moonlit-book-workflowgit clone --depth 1 https://github.com/lincwang123-bot/moonlit-storiesWrote 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/lincwang123-bot/moonlit-stories/moonlit-book-workflow)<a href="https://agentmods.dev/skills/lincwang123-bot/moonlit-stories/moonlit-book-workflow"><img src="https://agentmods.dev/badge/skills/lincwang123-bot/moonlit-stories/moonlit-book-workflow/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/lincwang123-bot/moonlit-stories/moonlit-book-workflow"><img src="https://agentmods.dev/badge/skills/lincwang123-bot/moonlit-stories/moonlit-book-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 30 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00078 | $0.01105 |
| Opus 5 | $0.00039 | $0.00553 |
| Sonnet 5 | $0.00016 | $0.00221 |
| Haiku 4.5 | $0.00008 | $0.00111 |
Grade A, and why
moonlit-book-workflow 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.
Moonlit Book Workflow
Purpose
Produce one personalized English picture book as a resumable local job. Keep story content variable while locking the illustration style with the approved neutral style key and one per-book character sheet. Render narration locally only from an authorized adult voice profile.
This skill orchestrates Codex tools and the project CLI. The browser application does not call Codex image generation directly.
Locate The Project
Use the current workspace when it contains scripts/book-workflow.mjs and workflow/styles/moonlit-watercolor-v1/style.json. Otherwise ask the user to open or provide the Moonlit Stories repository; never guess a user-specific absolute path. Refer to the repository root as PROJECT_ROOT in commands.
Do not put jobs, voice references, model weights, or generated private assets in source control. Use PROJECT_ROOT/.moonlit/jobs and PROJECT_ROOT/.local-models. A form-created job may keep its normalized narrator profile under that job's private/voice/ directory; never move it into public assets.
Required Workflow
- Read workflow-contract.md, image-generation.md, and tts-and-release.md before acting.
- Run
node scripts/book-workflow.mjs listfirst. If the user supplied the job ID returned by the browser form, inspect it withnode scripts/book-workflow.mjs status --job-id JOB_IDand read itsmanifest.json. Resume that exact job; do not recreate it. For a new job without an ID, derive a filesystem-safe ID such as20260803-luna-lantern, report it, and use it consistently. - Ensure the profile has a separate Latin-script
english_name. If the form supplied only a Chinese name, propose an English name or pinyin and get guardian confirmation before creating the job; never insert Han characters into English narration. - Create a job from a validated child profile when no job exists.
- Draft exactly 12 pages. Each page has one English sentence, one faithful Chinese translation, and one scene prompt. English narration must use the child's chosen English name and contain no Han characters.
- Commit the story and run
plan. Review the resulting prompt/task manifest before image generation. - Generate the character sheet first with built-in image generation. Inspect it visually. Record the exact returned file path, then approve it.
- Generate the cover and pages 1–12 with both the neutral style key and the approved character sheet as references. Inspect every candidate before approval.
- Inspect
manifest.narration. When it isparent-clone/ready, reuse the normalized profile atprivate_profile_pathinside the job; do not ask the user to upload it again and do not expose its transcript or consent file. When it isstandard/pending, finish story and illustrations, then stop at the TTS gate and ask for an authorized adult recording. Run local TTS only from an explicitly authorized adult profile. Never clone a child or an unconsenting person. - Record and approve all 12 narration files, assemble
book.json, validate the job, and build a self-contained reader HTML. - Before making a shareable HTML, obtain guardian confirmation for the chosen child display name and generated likeness. Keep full profile details in the private manifest and publish only reader-required fields.
- Open the result in the in-app browser and verify desktop and mobile rendering, page navigation, Chinese toggle, and audio playback. Close temporary servers and browser sessions started for testing.
What ships with it
4 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 · 57 lines · 78 tokens per session scan A fb84864075db
moonlit-book-workflow is a skill published in the GitHub repository lincwang123-bot/moonlit-stories (171 stars, last pushed 7d ago), licensed MIT. It adds 78 tokens to every session and 1,105 once invoked, about $0.0004 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.