agentmods.dev

pi-ai-library

pi-ai-library is a skill for Claude Code from romiluz13/pi-agent-skills. It costs 90 tokens per session (410 once invoked), scanned A, original, MIT.

A programming library that provides one interface for streaming responses from different language models, calling tools, tracking usage, and handing work between model providers.

In plain words
What is it for?
Use it to integrate supported language models, stream or complete requests, define tools, read thinking and usage events, and hand work from one provider to another.
Why use it?
Using several model providers can otherwise require different APIs and response-handling code. A shared interface reduces those differences when building AI features.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions AGENTS.md.

Part of the pi-skill plugin — 11 skills shipped together

not rated 20repo 7mo ago A scan 90 tokens original MIT

Good fit Use it to integrate supported language models, stream or complete requests, define tools, read thinking and usage events, and hand work from one provider to another.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/romiluz13/pi-agent-skills/pi-ai-library
View source ↗ romiluz13/pi-agent-skills
Install

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.

Any agent
npx skills add romiluz13/pi-agent-skills --skill pi-ai-library
Clone the repo
git clone --depth 1 https://github.com/romiluz13/pi-agent-skills

Made for: Claude Code.

Or install pi-skill, the plugin that ships this one along with the rest of its 11 skills.

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 pi-ai-library

README.md
[![agentmods](https://agentmods.dev/badge/skills/romiluz13/pi-agent-skills/pi-ai-library/github.svg)](https://agentmods.dev/skills/romiluz13/pi-agent-skills/pi-ai-library)
Your own site
<a href="https://agentmods.dev/skills/romiluz13/pi-agent-skills/pi-ai-library"><img src="https://agentmods.dev/badge/skills/romiluz13/pi-agent-skills/pi-ai-library/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 pi-ai-library

Your own site · 80×15
<a href="https://agentmods.dev/skills/romiluz13/pi-agent-skills/pi-ai-library"><img src="https://agentmods.dev/badge/skills/romiluz13/pi-agent-skills/pi-ai-library.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 410 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00090 $0.00410
Opus 5.5 $0.00036 $0.00164
Sonnet 5.5 $0.00018 $0.00082
Haiku 4.5 $0.00009 $0.00041

Measured 2mo ago against content hash 0482f4f5922d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pi-ai-library 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 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.

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.

pi-skills/pi-ai-library/SKILL.md · 28 lines

What it actually says

Pi AI library (@mariozechner/pi-ai)

Grounding

  1. pi-mono/packages/ai/README.md — primary API surface, providers list, examples.
  2. pi-mono/AGENTS.md — section Adding a New LLM Provider (packages/ai) (file checklist: types.ts, providers/, register-builtins.ts, tests, coding-agent touchpoints).
  3. pi-mono/packages/ai/src/ — read only the specific provider or type files needed after narrowing via README.

Invariants

  • Library scope is tool-capable models — stated in pi-mono/packages/ai/README.md opening note.
  • Provider work spans multiple files — follow pi-mono/AGENTS.md checklist verbatim when changing pi-mono.

Workflows

  • Call pattern: Use README Quick Start for stream / complete / Context / Tool shapes; cite line ranges by re-reading the file, do not paraphrase signatures from memory.
  • New provider: Execute the AGENTS.md checklist in order; link each step to the listed paths.

Anti-patterns

  • Do not document providers that appear only in other products; enumerate from pi-mono/packages/ai/README.md Supported Providers section.
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 28 lines · 0 tokens per session scan A 0482f4f5922d

Subscribe to this mod's changes

pi-ai-library is a skill published in the GitHub repository romiluz13/pi-agent-skills (20 stars, last pushed 7mo ago), licensed MIT. It adds 90 tokens to every session and 410 once invoked, about $0.0004 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.

Backend and APIsBuilding agents
Related

pi-ai-library compared with skills from other repositories

pi-ai-library next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pi-ai-libraryromiluz13/pi-agent-skillsSkill207mo agoMITA90Claude Code
mem0-oss-to-platformmem0ai/mem0Skill69k3d agoApache-2.0A217Claude Code, Codex
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2ktodayMITA78Claude Code
fastapi-router-pymicrosoft/skillsSkill3.2ktodayMITA46Claude Code
dev-runtimelangwatch/langwatchSkill5.0ktodayApache-2.0A172Claude Code
api-designericrisco/rsc-harnessSkill573todayMITA105Claude Code, Codex
migrate-segw-to-raparc-mcp/arc-1Skill254todayMITA106Claude Code