Home / vasilyu1983 / ai-agents-public · frameworks/shared-skills/skills/ai-coding-agents-provider-runtime/SKILL.md · GitHub

ai-coding-agents-provider-runtime skillA

ai-coding-agents-provider-runtime is agent-read markdown (skill) from vasilyu1983/ai-agents-public: Designs provider runtimes for coding agents. Use when modeling model abstraction, streaming semantics, tool-call normalization, retries, or fallback routing..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# AI Coding Agents Provider Runtime

Use this skill to design or review the model-provider layer inside a coding-agent runtime: provider abstraction, streaming semantics, tool-call protocol normalization, context-window strategy, retries, and fallback routing.

This skill owns the model-facing runtime surface for coding agents. It is the main missing layer when trying to generalize Claude Code-derived patterns toward Codex-class portability.

## ASCII Flow

```text
agent turn
  |
  v
provider selection
  capability needs + model policy + cost/latency + context window
  |
  v
request normalization
  messages + tools + structured outputs + cache hints + metadata
  |
  v
provider stream
  tokens + tool calls + errors + usage events
  |
  v
runtime event model
  normalized deltas + retries/fallbacks + final response
```

## Quick Reference

| Question | Read | Outcome |
|----------|------|---------|
| How should providers and streaming semantics be normalized? | [`references/provider-abstraction-and-stream-normalization.md`](references/provider-abstraction-and-stream-normalization.md) | Stable provider interface, streaming event model, and tool-call normalization |
…

Read the whole file at its exact version.

How to install

Latest version
mdr add vasilyu1983/ai-agents-public/ai-coding-agents-provider-runtime@v1.1
Exact content
mdr add vasilyu1983/ai-agents-public/ai-coding-agents-provider-runtime@sha256:4c95a11958154743

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_3s6hzptxqkjhl6mp.svg)](https://markdownregistry.com/a/art_3s6hzptxqkjhl6mp)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
v1.1 latest2026-09-23 8dc5de4 22,580 BA view · diff
v1.12026-08-09 da9d28f 22,054 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (22580 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

vasilyu1983/ai-agents-public · 88 stars · license MIT · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_3s6hzptxqkjhl6mp
GET https://markdownregistry.com/api/v1/resolve?ref=vasilyu1983/ai-agents-public/ai-coding-agents-provider-runtime
GET https://markdownregistry.com/api/v1/blob/4c95a1195815474377acc7d0e07fb0a6651d3de2f720ca1ce360a6802655c53b

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from vasilyu1983/ai-agents-public

AGENTS.md@frameworks/shared-skills agents
vasilyu1983/ai-agents-public · frameworks/shared-skills/AGENTS.md
git:20260923.8dc5de4 · audit A · 88 stars
agents-hooks skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/agents-hooks/SKILL.md · Configures Claude Code hooks and Codex hooks.json/notify callbacks. Use when adding guardrails, preflight, audit…
v1.5 · audit A · 88 stars
agents-mcp skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/agents-mcp/SKILL.md · Configures and hardens MCP servers for Claude Code and Codex agents. Use when connecting databases, APIs, files, or…
v1.5 · audit A · 88 stars
agents-memory skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/agents-memory/SKILL.md · Manages AGENTS.md, CLAUDE.md, and scoped repo rules for Claude Code and Codex. Use when fixing stale memory, ignored…
v1.4 · audit A · 88 stars
agents-skills-feedback-loop skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/agents-skills-feedback-loop/SKILL.md · Adds per-skill learnings loops for dated patterns, mistakes, and domain facts. Use when wiring skill memory…
v1.1 · audit A · 88 stars
agents-skills skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/agents-skills/SKILL.md · Creates and audits agent skills with SKILL.md, references, scripts, and platform-scoped metadata. Use when creating…
v1.2 · audit A · 88 stars
agents-swarm-orchestration skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/agents-swarm-orchestration/SKILL.md · Coordinates multi-agent execution across subagents, teams, and workflows. Use when planning dependency-aware fan-out…
v1.6 · audit A · 88 stars
ai-agents skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/ai-agents/SKILL.md · AI agent architecture, graph and loop composition, protocol choice, evaluation, and observability. Use when scoping or…
v1.1 · audit A · 88 stars
ai-architecture-advisor skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/ai-architecture-advisor/SKILL.md · Chooses among AI/ML approaches: classical ML, LLM, RAG, fine-tuning, agents, multimodal, embeddings/recsys…
v1.7 · audit A · 88 stars
ai-coding-agents-command-runtime skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/ai-coding-agents-command-runtime/SKILL.md · Designs slash-command runtimes for coding-agent CLIs. Use when modeling command registries, lazy loading, aliases…
v1.1 · audit A · 88 stars
ai-coding-agents-execution-sandbox skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/ai-coding-agents-execution-sandbox/SKILL.md · Designs execution sandboxes for coding agents. Use when modeling process isolation, filesystem policy, network…
v1.1 · audit B · 88 stars
ai-coding-agents-observability-evals skill
vasilyu1983/ai-agents-public · frameworks/shared-skills/skills/ai-coding-agents-observability-evals/SKILL.md · Designs coding-agent observability and evals. Use when measuring traces, replay, checkpoint lineage, quality…
v1.2 · audit A · 88 stars

Every file in vasilyu1983/ai-agents-public

Browse by kind, by grade A, or by owner.