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 skills/modem-dev/sideshow/sideshow-termnpx skills add modem-dev/sideshow --skill sideshow-termgit clone --depth 1 https://github.com/modem-dev/sideshowWhat 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 | $0.00085 | $0.00917 |
| Opus 5 | $0.00043 | $0.00458 |
| Sonnet 5 | $0.00017 | $0.00183 |
| Haiku 4.5 | $0.00009 | $0.00092 |
Grade A, and why
sideshow-term scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
sideshow-term guide # or: curl -s $SIDESHOW_URL/guide How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sideshow-term
The user keeps a live terminal visual surface open (sideshow-term watch). You
publish STML — an HTML-like markup — and it renders instantly as real
opentui components (boxes, borders, big ASCII text, styled text, lists, menus).
This is a higher-fidelity surface than the text you normally print.
Before your first publish
Fetch the markup contract once per session:
sideshow-term guide # or: curl -s $SIDESHOW_URL/guide
If SIDESHOW_URL is unset, the surface is at http://localhost:4243. If the
server is not running, start it: sideshow-term serve. If the
sideshow-term command is not on PATH but you are inside this repo, use
node sideshow-term/bin/sideshow-term.js ....
Publishing
Prefer MCP tools if connected (publish_snippet, update_snippet,
list_snippets). Otherwise use the CLI — session grouping is automatic:
sideshow-term publish sketch.stml --title "Cache layout" --session-title "Cache redesign"
echo '<h1>Done</h1><text>Migration applied.</text>' | sideshow-term publish - --title "Status"
Save the returned sessionId and snippet id. Iterate with
sideshow-term update <id> revised.stml (same card, new version) instead of
publishing near-duplicates — versions are kept. Preview without the viewer:
sideshow-term render sketch.stml.
To remove stale visuals before replacing a board, run sideshow-term clear for
the current session or sideshow-term clear --all for every session on the
surface.
Rules of thumb:
- On your first publish, set a session title that names the task ("Auth refactor"), not the tool. It applies only when the session is created.
- One concept per snippet, with a clear title. A series of small snippets beats one giant page.
- Reach for
<card>,<row>/<col>,<list>,<bigtext>and the semantic color tokens (accent,success,danger,warning,info,muted) before hand-tuning layout.
Writing STML
Block tags: box row col card text h1 h2 h3 list/item hr spacer bigtext code select input. Inline tags (inside <text>/headings): b i u s dim color/c kbd badge a br. Layout attributes on blocks: width height padding margin gap direction align justify grow border border-style border-color bg title.
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 · 90 lines · 85 tokens per session scan A 72af88417e94
sideshow-term is a skill published in the GitHub repository modem-dev/sideshow (567 stars, last pushed 5d ago), licensed MIT. It adds 85 tokens to every session and 917 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.