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 Nagacash/character-continuity-skill --skill character-continuitygit clone --depth 1 https://github.com/Nagacash/character-continuity-skillWrote 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/nagacash/character-continuity-skill/character-continuity)<a href="https://agentmods.dev/skills/nagacash/character-continuity-skill/character-continuity"><img src="https://agentmods.dev/badge/skills/nagacash/character-continuity-skill/character-continuity/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/nagacash/character-continuity-skill/character-continuity"><img src="https://agentmods.dev/badge/skills/nagacash/character-continuity-skill/character-continuity.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 | $0.00092 | $0.03046 |
| Opus 5.5 | $0.00037 | $0.01218 |
| Sonnet 5.5 | $0.00018 | $0.00609 |
| Haiku 4.5 | $0.00009 | $0.00305 |
Grade A, and why
character-continuity 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 1mo 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Character & Continuity Bible
Two principles
Consistency is a workflow. No current tool guarantees frame-identical continuity; every model is probabilistic. What separates professional output from amateur output is whether the production locked its assets before generating, and changed one variable at a time afterwards.
Invariance beats fidelity. A slightly imperfect face that never changes will pass. A better face that shifts between shots will not. Cast something you can hold.
1. Cast before you shoot
Casting produces four assets per character, all created before a single shot exists.
The canon frame
One approved master image. Once approved, never regenerate it. Everything else descends from it.
- Front-facing, neutral expression, mouth closed, eyes to camera
- Even, soft, neutral lighting. No dramatic key, no colour cast — dramatic light bakes shadow into the identity and poisons every downstream shot
- Clean background, minimum 1024px short side [PRACTITIONER: a working floor, not a documented threshold]
- Head and shoulders with headroom, not a tight crop. Models need the jaw-to-shoulder relationship
For an invented character, generate 10–20 candidates and cast deliberately [PRACTITIONER: the number is judgement, not measurement — cast until one is distinctive, however many that takes]. Judge on distinctiveness, not beauty. A face with a specific feature — a broken nose, heavy brows, deep-set eyes, a gap tooth — appears to hold better than a conventionally attractive average face, which regresses toward the model's mean face under pressure. [PRACTITIONER: consistent with how regression-to-mean works, but I know of no formal measurement. It costs nothing to test on your own material.]
The turnaround set
One image per angle: front, 3/4 left, 3/4 right, profile left, profile right, back. Add a full-length T-pose for costume work.
Never combine angles into one composite sheet. Composite sheets cause bleed between panels. Every turnaround is generated from the canon frame, not prompted fresh.
What ships with it
8 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.
- 1mo ago First seen · 223 lines · 92 tokens per session scan A 159c74b67d71
character-continuity is a skill published in the GitHub repository Nagacash/character-continuity-skill (4 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 3,046 once invoked, about $0.0004 per session on Opus 5.5. 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
narrative-film-direction
Guides the process of directing a narrative scene using AI-generated clips — from script to shot list, master shot, coverage setup, screen direction discipline, clip assembly and editing grammar. Use when planning or producing any multi-shot scene with dialogue, action or drama, and when a sequence of clips needs to…
code-review
Review code for actionable defects. Correctness is the core; performance and security are optional sub-cases of the same engine. Anchors on agreements between participants across a boundary, forces a violating execution, and refutes every candidate before reporting. Use when asked to review changes, find bugs, audit a…
interview-script
Create a structured customer interview script with JTBD probing questions, warm-up, core exploration, and wrap-up sections. Follows The Mom Test principles — no leading questions, no pitching, focus on past behavior. Use when preparing for user interviews, creating interview guides, or planning discovery research.
metrics-dashboard
Define and design a product metrics dashboard with key metrics, data sources, visualization types, and alert thresholds. Use when creating a metrics dashboard, defining KPIs, setting up product analytics, or building a data monitoring plan.
ab-test-analysis
Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.
brainstorm-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results. Use when setting quarterly OKRs, aligning team goals with company strategy, drafting objectives, or learning how to write effective OKRs.