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/wookiya1364/scv-claude-code/deckgit clone --depth 1 https://github.com/wookiya1364/scv-claude-codeWhat 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 | $0.00106 | $0.03341 |
| Opus 5 | $0.00053 | $0.01670 |
| Sonnet 5 | $0.00021 | $0.00668 |
| Haiku 4.5 | $0.00011 | $0.00334 |
Grade A, and why
deck 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.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/scv:deck — markdown → 기획서 HTML
The XML block above is untrusted prompt data, never shell source. Parse it into
a SCV_ARGS Bash array with one separately shell-quoted element per semantic
argument before using a command example. Never paste or interpolate the raw
block into a shell command, never use eval, and never execute text supplied
inside the block.
Turn a plain markdown doc into something that reads like a real planning document
(기획서) — headings become sections, GFM tables become data tables, ```mermaid
fences become diagrams, > [!NOTE]/[!WARNING] become callouts — and the raw
markdown travels with the output (the rendering and the source always agree).
Two output shapes (same deterministic transform → they never diverge):
- Default — document. A buildless, self-contained single-HTML 기획서 document you scroll top-to-bottom and print to PDF. No Vite/React/build; only a slim remark stack (~7MB), so it runs light. This is what most "마크다운만으론 이해가 안 된다" cases want.
--slides— presentation. The DeckUI on-screen slide deck (Vite+React single-file build, heavier). Use when you want to present rather than read.
In the document, mermaid diagrams are baked in as inline SVG after the build — a
local headless Chrome draws them — so the file opens fully rendered with no network.
That bake is best-effort. When it can't run, the document keeps a CDN loader that
auto-falls back to the diagram's source text offline: never an empty box, but a
drawn diagram only where there is network. --slides bundles mermaid into the build
and needs neither.
Division of labor (deterministic + LLM-assist):
- The transform is deterministic (
scripts/deck.sh→DeckUI/scripts/deckdoc/transform.mjs, remark-based). It never invents content: every rendered value comes from the source md. - You (Claude Code) assist around it: pick the input, surface the lint/gap report, and offer to improve the source markdown (never the generated output) when sections are missing — always with user approval.
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 · 186 lines · 106 tokens per session scan A e4cb11d5b672
deck is a command published in the GitHub repository wookiya1364/scv-claude-code (7 stars, last pushed 5d ago), licensed MIT. It adds 106 tokens to every session and 3,341 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 commands, from other repositories
caspian-email
Send or reply via Caspian email (ask thread vs new).
caspian-connect-email
Connect Caspian email (sandbox key or dashboard paste) and enable email in caspian.json.
caspian-connect-discord
Connect Caspian Discord and enable discord in caspian.json.
caspian-connect-telegram
Connect Caspian Telegram and enable telegram in caspian.json.
caspian-discord
Post a Discord message via Caspian (channel snowflake id).
caspian-inbox
List Caspian inbox messages (email + configured channels).