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 reverse-character-cardsgit 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/reverse-character-cards)<a href="https://agentmods.dev/skills/calliope-editor/writing-skills/reverse-character-cards"><img src="https://agentmods.dev/badge/skills/calliope-editor/writing-skills/reverse-character-cards/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/reverse-character-cards"><img src="https://agentmods.dev/badge/skills/calliope-editor/writing-skills/reverse-character-cards.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 | $0.00086 | $0.01930 |
| Opus 5 | $0.00043 | $0.00965 |
| Sonnet 5 | $0.00017 | $0.00386 |
| Haiku 4.5 | $0.00009 | $0.00193 |
Grade A, and why
reverse-character-cards 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read the manuscript and build a standard character card for each major player, reverse-engineered from what's actually on the page — not from what the author meant to put there.
The one rule
This skill reads, analyses, and documents. It never writes or rewrites the author's prose. It produces character cards about the fiction; it never adds a scene, a line of dialogue, or a backstory beat that isn't already on the page. If the wound is only implied, it marks it inferred rather than inventing it.
That restraint is also the point of the tool. Because it cards only what's demonstrated, it shows you the character who is actually on the page — which is not always the one you intended. The gap between the two is the most useful thing it hands back.
Intake — you don't need a character bible to start
You don't need to know your cast list or have any framework in mind. Open however you like — paste the manuscript and say "card my characters," name one person you're unsure about ("is Elena landing?"), or drop a chapter range. Deciding who's major and what a card needs is the skill's job, not yours.
Its first reply orients you in two quick moves: a one-line map (it reads the text → gathers each character's appearances → builds an evidence-anchored card), then a light intake:
- Scope — the whole manuscript, or a chapter range. It cards from as much as you give it and says what it couldn't see.
- Who to card — a specific character or two, or let it detect the major cast itself.
Then it reads.
The card
Each card is a lean, load-bearing profile — the ~8 fields that actually drive a story, tested by one filter: a field earns its slot only if it changes a choice the character makes under pressure (McKee's line between characterization and true character). Everything else — appearance, habits, favourites, full biography — is reference the card can expand into on request, but never leads with.
- Function — the role they serve and who they oppose in the story's web (protagonist, antagonist, foil, mirror, mentor); what they're there to test or prove.
- Want — the conscious, external goal driving them through the plot: a positive object they move toward, not merely a thing they flee.
- Need — the deeper, usually unconscious thing the story actually requires them to face — held as a separate field from Want. If a character's want and need point the same way, the card flags it: there's no arc engine there.
- Wound → Lie — the one load-bearing piece of backstory: the formative injury (the "ghost") and the false belief it planted, where the text supports them. Not a full timeline — only the wound that still bends present behaviour.
- Contradiction — the one consistent internal tension that makes them a person and not a type: competing drives, or the gap between how they see themselves and how they act. A major character with no contradiction is a flag, not a finding.
- Arc — how they change from first appearance to last — or whether they don't. The card reads it as change or steadfast (a steadfast character holds firm and changes the world around them); it never assumes a transformation that isn't on the page.
- Voice — diction, rhythm, verbal tics, and how their dialogue differs from the rest of the cast.
- Relationships — the web of allegiances, tensions, and dependencies with the other characters.
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 · 80 lines · 86 tokens per session scan A 924a8bc03379
reverse-character-cards is a skill published in the GitHub repository Calliope-Editor/writing-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 1,930 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 2026-08-31.
Other skills, from other repositories
story-import
A tool for turning an existing novel into a structured writing project. It analyzes the book and organizes its characters, settings, plot plans, chapters, and tracking data for later writing.
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-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.
story-deslop
A writing editor for Chinese web novels that detects writing patterns often associated with AI-generated text and makes the prose feel more natural.
story-short-analyze
A Chinese-language guide for analysing short popular web fiction, such as stories published on 番茄, 故事会, or 知乎盐选. It examines the core premise, plot structure, emotional arc, twists, writing techniques, and reader appeal.
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.