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/pixeltable/pixeltable-skill/add-providergit clone --depth 1 https://github.com/pixeltable/pixeltable-skillWrote 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/commands/pixeltable/pixeltable-skill/add-provider)<a href="https://agentmods.dev/commands/pixeltable/pixeltable-skill/add-provider"><img src="https://agentmods.dev/badge/commands/pixeltable/pixeltable-skill/add-provider.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 | $0.00019 | $0.00448 |
| Opus 5 | $0.00010 | $0.00224 |
| Sonnet 5 | $0.00004 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
add-provider 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 yesterday.
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.
What it actually says
Wire an AI provider into a Pixeltable table as a computed column. The model runs automatically on insert : never write a for row in ...: loop calling the model.
Request: $ARGUMENTS
Steps:
-
Identify the provider module under
pixeltable.functions.<provider>(e.g.openai,anthropic,gemini,groq,bedrock,together,fireworks,ollama,whisper). Confirm the exact import and output shape in thepixeltableskill (references/providers.md→ Quick Reference) before writing code. -
Add the call as a computed column, extracting the right field from the response. App file (assignment on the model):
from pixeltable.functions.openai import chat_completions
class Docs(TableModel, name='docs'):
content: pxt.String
summary = chat_completions(
messages=[{'role': 'user', 'content': content}],
model='gpt-4o-mini',
).choices[0].message.content
Then pxt schema update app.py my_app. Notebook / REPL:
from pixeltable.functions.openai import chat_completions
t.add_computed_column(
summary=chat_completions(
messages=[{'role': 'user', 'content': t.content}],
model='gpt-4o-mini',
).choices[0].message.content,
if_exists='ignore',
)
-
Set API keys via config/env, not hard-coded. API traps: SKILL.md. Stack: anti-patterns.md.
-
After adding, show how to insert a row and
collect()the result so the user can verify output shape.
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.
- yesterday Changed · +10 lines b319a3f6391f
- 3d ago Changed c532271799cf
- 5d ago First seen · 34 lines · 19 tokens per session scan A 529bbde7c74f
add-provider is a command published in the GitHub repository pixeltable/pixeltable-skill (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 19 tokens to every session and 448 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
doctor.es
Diagnostica problemas de inferencia LLM en Mac: asiai doctor verifica el estado de los motores, conflictos de puertos, carga de modelos y estado de la GPU.
web-add
Ingest a single URL into the knowledge base.
laravel-ai-sdk
Build AI features with the first-party Laravel AI SDK (Laravel 13+); use the laravel:ai-sdk skill exactly as written.
audit-prompt
Evaluate an existing prompt for clarity, effectiveness, and edge cases.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.