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 instructions/pixeltable/pixeltable-starter-kit/agents-mdgit clone --depth 1 https://github.com/pixeltable/pixeltable-starter-kitWrote 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/pixeltable/pixeltable-starter-kit/agents-md)<a href="https://agentmods.dev/instructions/pixeltable/pixeltable-starter-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/pixeltable/pixeltable-starter-kit/agents-md.svg" alt="Measured on agentmods" 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 | $0.00838 | $0.00838 |
| Opus 5 | $0.00419 | $0.00419 |
| Sonnet 5 | $0.00168 | $0.00168 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
pixeltable-starter-kit AGENTS.md 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 today.
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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents working in the Pixeltable Starter Kit.
Apps
Apps are one Python file (app.py): TableModel classes and a FastAPIRouter.
The loop is Declare, Experiment, Serve: apply with pxt schema update, serve with pxt service update or pxt service run, then insert / /ask / pxt dashboard.
If .venv is not on PATH after uv sync, prefix pxt with uv run.
Indexes belong on the model (__indexes__). Routes live on FastAPIRouter. No TOML route tables.
Already have FastAPI? app.include_router(...) on the router in app.py.
Same file on Cloud: pxt db update pxt://org:mydb, then
pxt secret set pxt://org KEY=..., then pxt schema update app.py pxt://org:mydb,
then pxt service update app.py pxt://org:mydb.
Then t = pxt.get_table('pxt://org:mydb/docs').
pxt db update packs the hosted image and workers; it is not Experiment.
pxt schema update applies tables. It does not start HTTP.
pxt service update starts HTTP (local or pxt://). pxt service run is local only.
Experiment on Cloud is dashboard insert plus pxt schema diff.
uvx pixeltable-new myapp
cd myapp && uv sync
pxt schema update app.py agent
pxt service update app.py agent
agent and videointel are catalog directories, not folders on disk.
Video: uvx pixeltable-new myapp --video, then TARGET videointel.
Layout
video-search/ Frames, CLIP, images. TARGET videointel. uvx --video
chat-agent/ Knowledge, memory, LLM. TARGET agent. uvx default
tests/ Structure and config. Schema smoke: --run-slow.
Do not add templates/, backend/, serving/, batch/, or a PaaS deploy/ zoo.
New verticals: edit app.py or add a folder next to these two with the same apply path.
Extend an app
- Add a
TableModelin that app'sapp.py. - Put indexes on the class (
__indexes__). - Register routes on the existing
FastAPIRouter. - Run
pxt schema update app.py agent(orvideointel).
Annotation is a stored column. Assignment is a computed column.
Primary key is pxt.Column(..., primary_key=True), not a bare typed field.
Optional is T | None. Do not use pxt.Required.
Similarity uses string=: col.similarity(string=query). In @pxt.query, alias as score=sim.
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.
- today Changed · -307 lines · -4,841 tokens per session 7cb0de6ec040
- 4d ago First seen · 385 lines · 5,679 tokens per session scan A ce010b963c2f
pixeltable-starter-kit AGENTS.md is an instructions file published in the GitHub repository pixeltable/pixeltable-starter-kit (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 838 tokens to every session, about $0.0042 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.