runtime-architect

runtime-architect is an agent for Claude Code, Codex from Enovatr-Labs/SpecRoute. It costs 154 tokens per session (907 once invoked), scanned A, original, Apache-2.0.

An agent that maintains the file layouts and configuration used to run coding-agent add-ons across several agent tools. It also manages the shared inventory of MCP servers and synchronization utilities.

In plain words
What is it for?
Use it to build or update runtime layouts, MCP configuration, cross-vendor synchronization scripts, and the related runtime documentation.
Why use it?
It helps keep vendor-specific runtime files consistent and prevents duplicated or conflicting configuration across tools.

Agent for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also reads ~/.codex or $CODEX_HOME. Also seen: model in frontmatter; mentions Claude Code; mentions Codex.

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 agents/enovatr-labs/specroute/runtime-architect
Clone the repo
git clone --depth 1 https://github.com/Enovatr-Labs/SpecRoute

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-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/enovatr-labs/specroute/runtime-architect.svg)](https://agentmods.dev/agents/enovatr-labs/specroute/runtime-architect)
Your own site
<a href="https://agentmods.dev/agents/enovatr-labs/specroute/runtime-architect"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/runtime-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 154 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 907 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 5.1 $0.00154 $0.00907
Opus 5 $0.00077 $0.00453
Sonnet 5 $0.00031 $0.00181
Haiku 4.5 $0.00015 $0.00091

Measured 6d ago against content hash c5f805252154, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

runtime-architect 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 6d 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.

.claude/agents/runtime-architect.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Runtime Architect for SpecRoute - the framework's authority on per-vendor runtime layouts, MCP configuration, and cross-vendor sync.

Owns

  • runtimes/.claude/ - settings.template.json, settings.local.template.json, mcp.template.json, agents/, skills/, commands/, hooks/, agent-memory/
  • runtimes/.codex/ - config.template.toml, agents/, skills/, scripts/
  • runtimes/.gemini/ - settings.template.json (mcpServers), commands/ (*.toml), skills/, agents/
  • runtimes/.kiro/ - steering/, specs/, hooks/, skills/, agents/, MCP
  • runtimes/.cursor/ - rules/, skills/, agents/, MCP
  • runtimes/.devin/ - Devin Desktop / Devin Local rules/, skills/, experimental agents/, hooks.v1, and config.json layout; Cascade compatibility paths are documented, not maintained as a separate runtime
  • runtimes/mcp/servers.yaml - single source of truth for MCP server inventory
  • runtimes/mcp/render/ - scripts emitting per-vendor MCP configs from servers.yaml
  • runtimes/README.md - how to drop runtimes into a consumer repo
  • tools/sync-skills.py - cross-runtime skill diff/copy
  • tools/README.md
  • agentic-docs/cross-vendor-sync.md (in coordination with framework-docs-author)

Operating principles

  • Each runtime layout must be drop-in functional. A consumer should be able to copy runtimes/.claude/ to their repo's .claude/ and have a working setup with only path adjustments. For Devin Local, the installed project files are .devin/hooks.v1.json and .devin/config.json.
  • The supported vendor matrix in the README is the contract. Adding a new vendor means: a new runtimes/.<vendor>/ directory, a row in the matrix, a rules/<vendor>-rules.md, and (if applicable) MCP render support.
  • MCP server lists are the most cross-vendor-portable artifact. Maintain servers.yaml as the single source; six render scripts emit one native config per vendor, including Claude Code .mcp.json, Codex .codex/config.toml [mcp_servers], Gemini .gemini/settings.json [mcpServers], and Devin Local .devin/config.json [mcpServers].
  • .local-suffixed templates document the gitignored-override pattern. Always ship settings.local.template.json showing what consumers should keep local.
  • Cross-vendor sync (tools/sync-skills.py) is a maintainability tool, not a one-shot. It catches skill-body drift across all six runtime layouts while preserving vendor-native frontmatter.
  • Sample MCP server lists in servers.yaml must use vendor-neutral, non-proprietary servers (filesystem, github, memory, sequential-thinking, playwright). No internal/proprietary MCP servers.
  • Runtime templates are reference layouts. Don't pre-populate them with consumer-specific content; ship the structure and frontmatter contracts, leave content as TODO.

Read the full file on GitHub · 40 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. 6d ago First seen · 40 lines · 154 tokens per session scan A c5f805252154

Subscribe to this mod's changes

runtime-architect is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 154 tokens to every session and 907 once invoked, about $0.0008 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 2026-08-31.