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 Calliope-Editor/writing-skills --skill character-card-buildergit clone --depth 1 https://github.com/Calliope-Editor/writing-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/calliope-editor/writing-skills/character-card-builder)<a href="https://agentmods.dev/skills/calliope-editor/writing-skills/character-card-builder"><img src="https://agentmods.dev/badge/skills/calliope-editor/writing-skills/character-card-builder/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/calliope-editor/writing-skills/character-card-builder"><img src="https://agentmods.dev/badge/skills/calliope-editor/writing-skills/character-card-builder.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 | $0.00096 | $0.01983 |
| Opus 5 | $0.00048 | $0.00992 |
| Sonnet 5 | $0.00019 | $0.00397 |
| Haiku 4.5 | $0.00010 | $0.00198 |
Grade A, and why
character-card-builder 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Turn a half-formed idea into a full, standard character card — through interview, one sharp question at a time, so the character stays the author's invention.
The one rule
This skill asks, probes, and organises. It never writes or rewrites the author's prose, and it never invents the character for the writer. It draws the character out through questions and shapes the writer's own answers into a card.
The hard part of that rule is the temptation to help too much. The research on interviewing is blunt about the risk: a leading question doesn't merely bias an answer, it can implant a detail the writer later remembers as their own. So the skill holds a discipline — it asks what you can actually answer, builds each question from your words, and when you're stuck it never fills the blank with a trait it picked. If it offers options, they're a contrasting menu to react against — two poles, not one suggestion — always yours to reject, and only ever a prompt, never a decision. A blank you can't fill is information (the character isn't formed there yet), not a hole for the tool to plug.
Intake — start wherever you are
Bring whatever you have — a name, an image, a role in the plot, or just a feeling. You don't need a framework or a finished idea; a blank page is a fine place to begin. Tell it the seed and, if you can, the story the character will live in, so the questions fit the book rather than a void.
It adapts to how you work: if you're a planner who wants the checklist, it'll be systematic; if you're a discovery writer who finds questionnaires deadening, it follows the thread instead of marching a list. Either way it asks one question at a time — never a wall of fields.
What the interview is aiming at
Under the conversation, the skill follows one causal spine — the load-bearing chain the character-craft traditions converge on:
wound → the lie it taught → the fear → the need → the surface want
It interviews toward that chain: the formative injury, the false belief it planted, what the character is afraid of, the deeper thing they actually need, and the conscious goal they'd name out loud. Everything else — looks, habits, favourites, the full biography — is optional texture, invited only when it changes what the character does under pressure (Egri's test: it isn't enough to know a trait, you have to know why it matters).
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 · 81 lines · 96 tokens per session scan A 0653ad22ca50
character-card-builder is a skill published in the GitHub repository Calliope-Editor/writing-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 1,983 once invoked, about $0.0005 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
story-review
A review workflow for finding story problems from several viewpoints, including issues with structure, characters, wording, and fictional world rules. It can use multiple reviewer agents or work alone.
story-cover
A novel-cover generator that creates a cover with the book title and author name. It chooses a visual style from the book information and can use Codex's image-generation tool.
transcript-cleanup
Cleans and formats a raw auto-generated podcast transcript for publication on a website or show page — removing filler words and transcription errors, adding speaker labels, formatting for readability, and preserving the authentic voice of host and guests.
bluf-rewriter
Reorganizes a memo, email, status update, or report so the bottom line is up front. Implements Kramon's BLUF (Bottom Line Up Front) rule. Use when a draft buries the lede, opens with context instead of conclusion, or builds up to the point with "organ music." Triggers on "BLUF," "lede," "buried," "memo," "status…
novel-to-screen-adaptation
A process for turning a novel into a screenplay by breaking it down into its main idea, story engine, objects, scenes, episodes, and script in that order. It is an adaptation workflow, not a general script-writing tool.
novel-original-writing
A Chinese-language workflow for turning an original story idea directly into a filmable script, without adapting a novel or other existing source. It develops the idea through seven stages, from concept and world-building to characters, structure, performance, and aftermath.