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 agentmods add commands/singhharsh1708/scrollcraft/scrollcraft-newgit clone --depth 1 https://github.com/singhharsh1708/scrollcraftWhat 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 | $0.00020 | $0.00297 |
| Opus 5 | $0.00010 | $0.00148 |
| Sonnet 5 | $0.00004 | $0.00059 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
scrollcraft-new 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 2d 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.
What it actually says
Start a new cinematic scroll site in the current directory.
Arguments (all optional): $ARGUMENTS — may contain a site name, and/or a style name from
aurora, nebula, tide, ember, dusk, monolith.
Steps:
- Read
${CLAUDE_PLUGIN_ROOT}/skills/scrollcraft/SKILL.mdand follow it. - Read
references/grammars.mdandreferences/taste.md. Pick a grammar for the page's shape and a style for its mood, from what the user described. Say which you picked and why. - Scaffold with
node "${CLAUDE_PLUGIN_ROOT}/skills/scrollcraft/scripts/init.mjs" --name "<name>" --style <style> --grammar <grammar>. - Rewrite the placeholder sections in
scrollcraft.jsonas real copy for their subject. One idea per section. Do not leave the starter text in place. - Vary each section's
layoutso consecutive screens do not share a shape. - Rebuild, run
doctor.mjsandverify.mjs, then serve it and tell them the URL and the measured contrast.
If they have their own footage, use frames-from-video.mjs instead of the procedural style.
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.
- 2d ago First seen · 22 lines · 20 tokens per session scan A 6eb3f976fe5d
scrollcraft-new is a command published in the GitHub repository singhharsh1708/scrollcraft (48 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 297 once invoked, about $0.0001 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.