pixeltable-skill: Instructions file for Codex

AGENTS.md

pixeltable-skill AGENTS.md is an instructions file for Codex, OpenCode from pixeltable/pixeltable-skill. It costs 807 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for the Pixeltable Agent Plugin, which teaches AI coding assistants to build applications with Pixeltable, a data and AI processing platform.

In plain words
What is it for?
Use it when adding or updating Pixeltable guidance, commands, specialist agents, hooks, or supporting documentation.
Why use it?
It explains the plugin structure, conventions, reference files, and validation rules so changes fit the project and remain installable.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions .claude-plugin; mentions AGENTS.md; mentions Codex.

This is pixeltable/pixeltable-skill's own configuration. It tells Codex and OpenCode how to work on pixeltable-skill itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pixeltable-skill configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pixeltable/pixeltable-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/pixeltable/pixeltable-skill/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/pixeltable/pixeltable-skill

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for pixeltable-skill AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pixeltable/pixeltable-skill/agents-md/github.svg)](https://agentmods.dev/instructions/pixeltable/pixeltable-skill/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/pixeltable/pixeltable-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/pixeltable/pixeltable-skill/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.

agentmods 80×15 button for pixeltable-skill AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pixeltable/pixeltable-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/pixeltable/pixeltable-skill/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 807 This file is loaded in full into every session.
When invoked 807 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00807 $0.00807
Opus 5.5 $0.00323 $0.00323
Sonnet 5.5 $0.00161 $0.00161
Haiku 4.5 $0.00081 $0.00081

Measured 3d ago against content hash b01b2b42312f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pixeltable-skill 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 3d 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.

AGENTS.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This repo is the Pixeltable Agent Plugin: one skill plus agents, slash commands, and optional hooks. Install via npx plugins add pixeltable/pixeltable-skill or npx skills add pixeltable/pixeltable-skill.

Structure

skills/pixeltable-skill/
├── SKILL.md
└── references/
    ├── core-api.md
    ├── cli.md
    ├── providers.md
    ├── workflows.md
    └── anti-patterns.md

commands/                 # /pixeltable:scaffold, add-provider
agents/                   # pipeline-architect, debugger
hooks/
scripts/validate_plugin.py
gemini-extension.json     # Gemini CLI extension + gallery listing
GEMINI.md                 # Gemini CLI context; points at skills/, does not copy them

Manifests: root plugin.json (portable), .plugin/plugin.json, .cursor-plugin/plugin.json, .claude-plugin/, .codex-plugin/ (compatibility), package.json, and gemini-extension.json. Keep name pixeltable and versions in sync (2.12.0).

Rules

  • Single skill. Do not split it.
  • Hooks are pure Python. No Node/Bun/TypeScript. hooks.json finds the interpreter itself (python, then python3, then py -3): a python.org install on Windows has no python3.exe (#23).
  • SKILL.md teaches the application file first. Notebook SDK is an appendix.
  • Start from pxt init then pxt service example --out app.py (or pxt schema example --brief). Then pxt schema update app.py my_app. No template zoo. No starter kit.
  • if_exists='ignore' on notebook create_* / add_*.
  • No LangChain, pandas-as-store, or standalone vector DB patterns.
  • Keep SKILL.md under 500 lines (enforced by validate_plugin.py).
  • Fenced ```python blocks in skills/, agents/, commands/, and GEMINI.md must pass the hook's own error checks -- the validator imports CHECKS and runs them. Quote a wrong form in prose or a traps table, never in a code block.
  • GEMINI.md is Gemini CLI session context. Point it at skills/pixeltable-skill/; do not duplicate SKILL.md. Gemini loads skills/*/SKILL.md on its own.
  • Since Pixeltable 0.7.10, editing a computed column's expression in place is a safe alter: pxt schema update applies it and keeps the old values until pxt recompute. A type change, including T to T | None, is still UNSUPPORTED: rename the column, or drop and re-add it. --allow-destructive does not help.
  • Agent-facing pxt service update examples carry -f: an agent has no TTY, and without the flag a pending update exits 3.
  • Run python3 scripts/validate_plugin.py, python3 tests/test_hooks.py and python3 tests/test_integrations.py after any change.
  • Re-verify against the current Pixeltable release before a version bump: the record of the last pass is docs/review-<skill version>.md.

Read the full file on GitHub · 48 lines

Changes

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.

  1. 3d ago Changed · +3 lines · +92 tokens per session b01b2b42312f
  2. 26d ago Changed · +1 lines · +85 tokens per session 6e810fa0a152
  3. 1mo ago Changed c29c27353c01
  4. 1mo ago Changed a239e6ee10d1
  5. 1mo ago Changed · +1 lines · +79 tokens per session 40d938b438ce
  6. 1mo ago Changed ab1e62320f39
  7. 1mo ago Changed ca8cc2aafd9c
  8. 1mo ago Changed · +13 tokens per session dd1b759c00b4
  9. 1mo ago Changed · +2 lines · +123 tokens per session 3bf4bc69445b
  10. 1mo ago First seen · 41 lines · 415 tokens per session scan A 59952594d17c

Subscribe to this mod's changes

pixeltable-skill AGENTS.md is an instructions file published in the GitHub repository pixeltable/pixeltable-skill (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 807 tokens to every session, about $0.0032 per session on Opus 5.5. 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.

Related

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).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,581 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens