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.
git clone --depth 1 https://github.com/Enovatr-Labs/SpecRouteWrote 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/agents/enovatr-labs/specroute/runtime-architect)<a href="https://agentmods.dev/agents/enovatr-labs/specroute/runtime-architect"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/runtime-architect/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.
<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="Reviewed on agentmods" width="80" 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 5.1 | $0.00154 | $0.00907 |
| Opus 5.5 | $0.00062 | $0.00363 |
| Sonnet 5.5 | $0.00031 | $0.00181 |
| Haiku 4.5 | $0.00015 | $0.00091 |
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 1mo 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.
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/, MCPruntimes/.cursor/- rules/, skills/, agents/, MCPruntimes/.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 runtimeruntimes/mcp/servers.yaml- single source of truth for MCP server inventoryruntimes/mcp/render/- scripts emitting per-vendor MCP configs from servers.yamlruntimes/README.md- how to drop runtimes into a consumer repotools/sync-skills.py- cross-runtime skill diff/copytools/README.mdagentic-docs/cross-vendor-sync.md(in coordination withframework-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.jsonand.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, arules/<vendor>-rules.md, and (if applicable) MCP render support. - MCP server lists are the most cross-vendor-portable artifact. Maintain
servers.yamlas 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 shipsettings.local.template.jsonshowing 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.yamlmust 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.
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.
- 1mo ago First seen · 40 lines · 154 tokens per session scan A c5f805252154
runtime-architect is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 8d ago), licensed Apache-2.0. It adds 154 tokens to every session and 907 once invoked, about $0.0006 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 2026-08-31.
Other agents, from other repositories
bootstrap
Use once per invocation, at the start of a new Hedgehog project, to land the workspace for whichever core planner selected at Phase 0 — the first real workspace this project gets, since init with no explicit core flag lands the shared agents/skills/build-graph payload and leaves the workspace to bootstrap. Reads the…
doc-onboard
Discovery and understanding of a codebase. Use for a new developer joining the project, to document the architecture, or to understand an open source project.
Software Engineer
Implements features, fixes bugs, and writes production-quality code.
ops-deps
Audit and analysis of dependencies. Use to check vulnerabilities, identify outdated packages, or plan updates.
ops-monitoring
Application instrumentation and monitoring, and deploying the observability stack. Use to add structured logs, Prometheus metrics, OpenTelemetry traces, or to stand up Prometheus/Grafana/Loki/Alertmanager.
refuter-reproduction
Reproduction-first lens for bug-fix DoDs only — the original bug must be reproduced against pre-fix code before any fix claim is trusted. Read-only. Invoked only by mnm-verify, only when the DoD's Goal is a bug fix.