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 ZSeven-W/craft-skills --skill recurring-character-diary-comicgit clone --depth 1 https://github.com/ZSeven-W/craft-skillsWrote 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/zseven-w/craft-skills/recurring-character-diary-comic)<a href="https://agentmods.dev/skills/zseven-w/craft-skills/recurring-character-diary-comic"><img src="https://agentmods.dev/badge/skills/zseven-w/craft-skills/recurring-character-diary-comic/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/zseven-w/craft-skills/recurring-character-diary-comic"><img src="https://agentmods.dev/badge/skills/zseven-w/craft-skills/recurring-character-diary-comic.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 Output Handling · line 54 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
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 | $0.00129 | $0.02208 |
| Opus 5 | $0.00064 | $0.01104 |
| Sonnet 5 | $0.00026 | $0.00442 |
| Haiku 4.5 | $0.00013 | $0.00221 |
Grade A, and why
recurring-character-diary-comic 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recurring Character Diary Comic
Turn a concrete observation into one coherent comic page while preserving an authorized recurring identity. The default is page-native generation: the image model solves the complete page, not a collection of independent cards.
Load only the needed references
- Read references/character-profile-schema.md when creating or interpreting a recurring-character profile.
- Read references/story-rhythm.md before selecting a premise, writing dialogue, or planning beats.
- Read references/visual-task-contract.md before locking evidence, comparing page skeletons, scoring risk, or selecting a production route.
- Read references/continuity-and-visual-qa.md before auditing, repairing, or accepting a rendered page.
- Read references/editorial-layout-gate.md before accepting a final page or using it as a public example.
- Read references/compositor-manifest.md and use scripts/compose_panels.py only when lettering a complete unlettered page or when an explicitly accepted fallback reconstructs a page from independent panels.
- Follow the available image-generation skill when generating or editing raster artwork.
Choose the mode
- Create: require an existing authorized recurring identity, pass the premise gate, lock story and visual evidence, compare three page structures, generate one complete page, and inspect the final pixels.
- Audit: inspect an existing page against its approved character and story records; report evidence without silently editing it.
- Repair: audit first, name the failing field, and prefer one bounded local page edit. Reconstruct panels only under the fallback rule below.
Do not expand the request into character design, branding, publishing, or an unrelated illustration task.
What ships with it
16 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 737 B
- README.en.md 6.9 KB
- README.md 11 KB
- references/character-profile-schema.md 6.2 KB
- references/compositor-manifest.md 14 KB
- references/continuity-and-visual-qa.md 16 KB
- references/editorial-layout-gate.md 5.4 KB
- references/story-rhythm.md 7.7 KB
- references/visual-task-contract.md 19 KB
- scripts/compose_panels.py 86 KB runs code
- scripts/requirements.txt 15 B
- scripts/self_test_compositor.py 40 KB runs code
- templates/compositor-manifest.example.json 4.7 KB
- templates/editorial-layout-gate.example.yaml 1.9 KB
- templates/page-native-lettering-manifest.example.json 2.0 KB
- templates/visual-task-contract.example.yaml 5.2 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.
- 12d ago First seen · 96 lines · 129 tokens per session scan A b4b7e621fccd
recurring-character-diary-comic is a skill published in the GitHub repository ZSeven-W/craft-skills (149 stars, last pushed 6d ago), licensed Apache-2.0. It adds 129 tokens to every session and 2,208 once invoked, about $0.0006 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
html-ppt-zhangzara-retro-zine
A neighborhood zine on the disappearing corner shops — portraits, voices, and what a block loses when they close. Built as a decision-grade story deck for community, local readers.
html-ppt-zhangzara-studio
A photography studio's portfolio-and-rate deck — the signature work, the process, and the packages that win the brief. Built as a decision-grade design craft deck for prospective clients.
motion-frames
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…
webgl-halftone-drift
A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.
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.
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…