agentmods.dev

runtime-change

runtime-change is a skill for Claude Code, Codex from BlocUnited-LLC/mozaiks. It costs 34 tokens per session (2,184 once invoked), scanned A, original, MIT.

A project-specific guide for changing the Mozaiks runtime, the software that loads modules and handles application requests. It covers composition, authentication, transport, storage and routing.

In plain words
What is it for?
Use it when modifying runtime hosts, module loading or dispatch, authentication, communication layers, persistence, extensions or related architecture and tests.
Why use it?
It helps changes fit the platform’s architecture and keeps module loading, execution and request handling within the project’s boundaries.

Skill for Claude CodeCodex

not rated 25 +1 yesterday A scan 34 tokens original MIT
View the source file BlocUnited-LLC/mozaiks
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.

agentmods
npx agentmods add skills/blocunited-llc/mozaiks/runtime-change
Any agent
npx skills add BlocUnited-LLC/mozaiks --skill runtime-change
Clone the repo
git clone --depth 1 https://github.com/BlocUnited-LLC/mozaiks

Made for: Claude Code, Codex.

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 runtime-change

README.md
[![agentmods](https://agentmods.dev/badge/skills/blocunited-llc/mozaiks/runtime-change.svg)](https://agentmods.dev/skills/blocunited-llc/mozaiks/runtime-change)
Your own site
<a href="https://agentmods.dev/skills/blocunited-llc/mozaiks/runtime-change"><img src="https://agentmods.dev/badge/skills/blocunited-llc/mozaiks/runtime-change.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,184 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00034 $0.02184
Opus 5 $0.00017 $0.01092
Sonnet 5 $0.00007 $0.00437
Haiku 4.5 $0.00003 $0.00218

Measured 5d ago against content hash 3f8bbf0f420b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runtime-change 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 5d 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/skills/runtime-change/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Before starting: git fetch origin && gh pr list --state open && git log origin/main --oneline -3 — if another agent has an open PR touching the same files you need, wait for it to merge or branch off it instead of main.

Use this skill when a change touches the OSS runtime or platform host.

Typical triggers:

  • mozaiksai/hosts/runtime.py
  • mozaiksai/hosts/platform.py
  • mozaiksai/core/runtime/app/module_loader.py
  • mozaiksai/core/runtime/composition/module_executor.py
  • mozaiksai/core/runtime/composition/module_event_router.py
  • mozaiksai/core/runtime/composition/module_context.py
  • mozaiksai/core/runtime/composition/platform_hooks.py
  • mozaiksai/core/runtime/composition/extensions.py
  • mozaiksai/core/auth/**
  • mozaiksai/core/transport/**
  • mozaiksai/core/runtime/persistence/**

Inspect first:

  • ARCHITECTURE.md
  • AGENTS.md
  • CLAUDE.md
  • .claude/rules/runtime.md
  • .claude/rules/architecture-boundaries.md
  • .claude/rules/testing.md
  • docs/architecture/app/platform-authoring.md when app loading, shell, route ownership, or module dispatch changes
  • docs/architecture/modules-systems/module-system.md when module contracts or module runtime composition change
  • docs/architecture/foundations/events-and-data/persistence-and-artifact-storage.md when ctx.persistence, data contract, indexes, or migrations change
  • factory_app/build_context/AppGenerator/file_contracts.yaml when generated app or module contracts depend on the runtime behavior
  • the owning runtime file and its narrowest test slice before editing:
    • mozaiksai/hosts/runtime.py + tests/test_runtime_websocket_contract.py or tests/test_auth_oidc_discovery.py
    • mozaiksai/hosts/platform.py + tests/test_platform_ai_config_resolution.py, tests/test_platform_layout.py, or tests/test_platform_shell_p0_fixes.py
    • mozaiksai/core/runtime/app/module_loader.py + tests/test_module_loader_contracts.py
    • mozaiksai/core/runtime/composition/extensions.py + tests/test_module_runtime_extensions.py
    • mozaiksai/core/runtime/composition/module_executor.py / mozaiksai/core/runtime/composition/module_context.py + tests/test_runtime_persistence_module_injection.py
    • mozaiksai/core/runtime/composition/platform_hooks.py + tests/test_platform_hook_registry.py
    • mozaiksai/core/runtime/composition/module_event_router.py + tests/test_module_loader_contracts.py
    • generated-app dependency checks + tests/test_appgenerator_canonical_generation.py or tests/test_appgenerator_persistence_alignment.py when AppGenerator assumptions are touched

Current runtime truth:

  • the runtime host is the universal substrate for auth, transport, workflow execution, persistence primitives, and event delivery
  • the platform host owns app loading, module execution, module event meaning, runtime extension mounting, admin and profile discovery, and shell or route composition
  • ModuleLoader validates module.yaml, companion contracts, and runtime_extensions.yaml
  • ModuleExecutor builds ModuleContext, enforces action permissions and schemas, injects ctx.persistence, and emits declared events
  • ModuleEventRouter is platform-owned interpretation of reactions, notifications, and capability dispatch on top of runtime event transport
  • AppGenerator and generated app fixtures may depend on these contracts; inspect the file contracts and fixture tests before changing behavior

Layer boundary rules:

  • Runtime = universal substrate for auth, transport, persistence primitives, workflow execution, session state, and event delivery
  • Platform = app workspace loading, module registration and execution, module event meaning, app shell, admin and profile wiring, runtime extension mounting, and route or module dispatch
  • Factory = build-time generation and file-contract ownership. Do not bury runtime policy in factory prompts, and do not change runtime behavior without checking generator expectations.
  • Hosted = external or hosted-only product capabilities. Do not put hosted-only product logic into runtime or platform code.
  • Module business logic stays in module handlers, services, and repos. Do not hardcode app-specific workflow or product rules inside runtime internals.
  • mozaiksai.core.auth authenticates. Do not smuggle authorization or product policy into generic auth adapters.
  • ModuleContext.persistence is ctx.persistence; do not reintroduce ctx.db.

Read the full file on GitHub · 143 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. 5d ago First seen · 143 lines · 34 tokens per session scan A 3f8bbf0f420b

Subscribe to this mod's changes

runtime-change is a skill published in the GitHub repository BlocUnited-LLC/mozaiks (25 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 2,184 once invoked, about $0.0002 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.

Backend and APIsLLMagent-frameworkagentic-aiaiai-agentsgenai
Related

Other skills, from other repositories

add-new-model

Add support for a newly-released LLM model in pydantic-ai (e.g. openai:gpt-5.6, anthropic:claude-sonnet-5). Use when a provider ships a new model id and you need to wire literals, profile flags, and tests to recognize it. Handles SDK-lag, gateway list conventions, and capability probing.

pydantic/pydantic-ai · 80 tokens

building-pydantic-ai-agents

Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…

pydantic/pydantic-ai · 85 tokens

complete-partial-pr

Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.

pydantic/pydantic-ai · 55 tokens

testing-skill

Record, rewrite, and debug VCR cassettes for HTTP recordings. Use when running tests with --record-mode, verifying cassette playback, or inspecting request/response bodies in YAML cassettes.

pydantic/pydantic-ai · 44 tokens

pre-push-review

Run a high-judgment local review of the current branch before pushing, both before a PR exists and between PR iterations.

pydantic/pydantic-ai · 24 tokens

adding-a-provider-api-feature

Add a new provider API capability (prompt caching, strict/structured tool calling, thinking/reasoning effort, service tier, safety settings, logprobs, etc.) to Pydantic AI. Use when wiring a provider feature through the library — it enforces reasoning from the existing cross-provider abstraction before designing…

pydantic/pydantic-ai · 97 tokens