Borrowing it
Nothing to install: this file belongs to modem-dev/sideshow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/modem-dev/sideshow/main/AGENTS.mdgit clone --depth 1 https://github.com/modem-dev/sideshowWrote 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/instructions/modem-dev/sideshow/agents-md)<a href="https://agentmods.dev/instructions/modem-dev/sideshow/agents-md"><img src="https://agentmods.dev/badge/instructions/modem-dev/sideshow/agents-md/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/instructions/modem-dev/sideshow/agents-md"><img src="https://agentmods.dev/badge/instructions/modem-dev/sideshow/agents-md.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 | $0.04254 | $0.04254 |
| Opus 5.5 | $0.01702 | $0.01702 |
| Sonnet 5.5 | $0.00851 | $0.00851 |
| Haiku 4.5 | $0.00425 | $0.00425 |
Grade A, and why
sideshow AGENTS.md 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 2mo 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.
all three — the CLI and curl tiers are why agents with only a shell can How it starts
The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sideshow — agent guide
Guidance for agents developing this repo. (The block that teaches agents to
use a running sideshow lives in guide/AGENT_SETUP.md, served at /setup.)
CLAUDE.md symlinks here.
What this is and why
A live visual surface for terminal coding agents: agents publish posts (multi-surface cards — html, markdown, diff, terminal, image, mermaid, json, code) over CLI/MCP/HTTP; the user watches them render in a browser and comments back. The two-way loop — publish → live render → comment → revise/reply — is the product. When in doubt, optimize for the loop.
Current product stances (deliberate choices, not accidents — revisit consciously, not as a side effect):
- One workspace per person; one session per agent conversation. Accounts and multi-user are out of scope; auth is a single deploy token.
- Three integration tiers, most universal first: zero-dependency CLI, MCP
(stdio and streamable HTTP at
/mcp), raw HTTP. Features should work on all three — the CLI and curl tiers are why agents with only a shell can use this. - Feedback is never silently lost: a user comment renders in the viewer (the
card's thread) and reaches the agent (
userFeedbackpiggybacked on writes, a blocking wait, or a background watch). Guard this hardest — both halves have regressed before. - Trace exists in the codebase as an experimental path. Keep it out of the product-facing surface taxonomy and agent guidance unless the task is explicitly about deciding or finishing traces.
Map
server/app.ts— runtime-agnostic Hono app: all routes, SSE/api/events, long-poll/api/comments, renderer/s/:id, asset upload/serve (/api/assets,/a/:id), and the shared flow functions both REST and MCP call.server/types.ts— data model +Storeinterface; no runtime imports. A post is an ordered list of surfaces (html|markdown|diff|terminal|image|mermaid|json|code); a snippet is sugar for a single html surface.htmlSurfacebridges the legacy snippet shape. Assets (uploaded blobs) are a separate entity, referenced byimagesurfaces and the experimental trace path;selectEvictionsis the reference-aware LRU policy.server/public.ts— thesideshow/serverpackage export (createApp,SqlStore,createSqliteStorage,JsonFileStore, types) for embedding the app.server/sqlStore.ts—SqlStore, the SQLite-backedStore. It takes aSqlStorage(the narrow SQL surface declared intypes.ts, not the ambient Cloudflare global), so the SAME store runs on the Durable Object (ctx.storage.sql) and on Node viaserver/sqliteStorage.ts'snode:sqliteadapter — the local default, so dev mirrors the deploy.server/storage.ts—JsonFileStore, the legacy single-file store, still selectable withSIDESHOW_STORE=json. All must passtest/storeContract.ts, and all migrate legacysnippets/snippetIddata to surfaces on load. On first SQLite bootmigrateJsonToSqlitecopies an existing JSON workspace in once (identity, history, and commentseqpreserved viaJsonFileStore.exportBoard→SqlStore.importBoard); it's idempotent and never imports into a non-empty db.server/kits.ts— opt-in style/behavior bundles for html surfaces (issues,slides). An html surface lists kit ids inkits;renderHtmlPageinjects each kit's CSS/JS into the sandbox after the base. Runtime-agnostic; allowlisted inserver/postSurfaces.tsand listed at/api/kits. Adding a kit is a registry entry + a guide bullet — no new surface kind, no native renderer.server/richRender.ts— server-side renderers for the rich kinds (renderMarkdown/renderCode/renderDiff/renderTerminal→{body, css}), runtime-agnostic so they run on the Worker DO too (shiki on the JS regex engine, @pierre/diffs SSR viashiki-js, markdown-it, ansi_up — no WASM/DOM)./s/:idcalls these and wraps the result inrenderSandboxedPart.server/surfacePage.ts— sandboxed documents for surface markup.renderHtmlPagewraps an html surface (CDN-allowlist CSP + the postMessage bridge: resize, sendPrompt, openLink) and injects any opted-in kits (kits.ts).renderSandboxedPartwraps a server-rendered rich body (markdown/code/diff/ terminal — seerichRender.ts) under a tighter CSP (noconnect-src, no CDN).renderMermaidPageis the one exception: mermaid needs a DOM, so it can't be server-rendered — instead it emits a self-rendering doc that loads mermaid from the CDN allowlist (so it uses the html-surface CSP, which permits the CDN). Image and json surfaces stay native because they have no HTML sink; the experimental trace path follows the same data-only rule. Comments render as escaped Solid text nodes. No agent markup is ever set asinnerHTMLin the trusted viewer origin.server/themes.ts— theme registry (github/gruvbox/one), runtime-agnostic so both server and viewer import it. OnePaletteper light/dark per theme; the viewer-chrome vars and the html-surface--color-*tokens are both derived from it, so they can't drift. Persisted per workspace (Store.getSetting), switched at/api/theme.server/mcpHttp.ts— stateless MCP at/mcp.mcp/server.ts— stdio MCP, a thin client over the HTTP API (passes response fields through untouched).viewer/— the viewer: Solid + TypeScript inviewer/src/, built by Vite (vite.config.ts) into a single self-containedviewer/dist/index.html(vite-plugin-singlefile) that the server still serves as one in-memory document — there are no static-asset routes.bin/sideshow.js— CLI, Node built-ins only;bin/demoData.js— seed content forsideshow demo.workers/index.ts— Cloudflare entry; one Durable Object runs the whole app.skills/sideshow/+guide/— teach agents to use a running sideshow.scripts/record-demo.mjs— regenerates the README gif.
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.
- 2mo ago First seen · 260 lines · 4,254 tokens per session scan A b1059399c783
sideshow AGENTS.md is an instructions file published in the GitHub repository modem-dev/sideshow (630 stars, last pushed 2mo ago), licensed MIT. It adds 4,254 tokens to every session, about $0.0170 per session on Opus 5.5. 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.
sideshow AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sideshow AGENTS.mdmodem-dev/sideshow | Instructions file | 630 | 2mo ago | MIT | A | 4,254 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |