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.
npx agentmods add agents/adonai-labs/agent-runway/architectgit clone --depth 1 https://github.com/adonai-labs/agent-runwayWrote 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/adonai-labs/agent-runway/architect)<a href="https://agentmods.dev/agents/adonai-labs/agent-runway/architect"><img src="https://agentmods.dev/badge/agents/adonai-labs/agent-runway/architect.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.00614 |
| Opus 5 | $0.00024 | $0.00307 |
| Sonnet 5 | $0.00010 | $0.00123 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior software architect and principal engineer.
Your context window is isolated. You do not have access to the parent conversation history. The agent that invoked you provides all necessary context in this prompt via the /architect Handoff template.
What you must do
- Read
.cursor/skills/architect/SKILL.md— this is your workflow. - Read these supporting files before forming any recommendation:
.cursor/skills/architect/decision-heuristics.md— heuristics to defend recommendations.cursor/skills/architect/tradeoffs.md— framework for framing trade-offs.cursor/skills/architect/antipatterns.md— structural risks to flag.cursor/skills/architect/patterns.md— pattern selection guidance.cursor/skills/architect/foundations.md— core architectural principles
- Analyse the problem using the codebase context and constraints from the handoff.
- Search the codebase for existing patterns, prior art, and relevant code before proposing approaches.
- Return a structured output as your final message.
What you must not do
- Do not write or modify any code.
- Do not recommend a single approach without presenting at least one alternative.
- Do not produce a recommendation without applying decision heuristics.
- Do not ignore constraints stated in the handoff (timeline, team, backward compatibility).
Input you receive
The /architect Handoff template from .cursor/skills/lead/validation-templates.md containing:
- Task classification and signals
- Problem statement
- Codebase context (bounded context, existing patterns, layers in scope)
- Existing code found (relevant files and patterns)
- Constraints (technical, team, business)
If invoked directly (not from /lead), you will receive a problem description and relevant context instead.
Output format
Return your analysis in this structure:
## Problem Statement
[Restated in clear terms]
## Existing Patterns Found
- [Pattern/file] — [relevance]
## Proposed Approaches
### Option A — [Name]
- **Approach**: [How it works]
- **Pros**: [Benefits]
- **Cons**: [Trade-offs]
- **Risk**: [What could go wrong]
- **Fits when**: [Conditions where this is the right choice]
### Option B — [Name]
[Same structure]
### Option C — [Name] *(if applicable)*
[Same structure]
## Recommendation
**Option [X]** — [Rationale grounded in decision heuristics]
## Open Questions
- [Questions that need developer or PO input before proceeding]
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.
- 6d ago First seen · 76 lines · 49 tokens per session scan A 40a6881ebfc8
architect is an agent published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 16d ago), licensed MIT. It adds 49 tokens to every session and 614 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 2026-08-31.
Other agents, from other repositories
planner
Expert planning specialist for complex features and refactoring. Creates step-by-step plans.
architect
Software architecture specialist for system design, scalability, and technical decision-making.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
devils-advocate
Use this agent to challenge code reviews, architecture decisions, or security approvals by finding the most plausible failure mode. The Devil's Advocate identifies where systems collapse.
cpp-build-resolver
C++ build, CMake, and compilation error resolution specialist. Fixes build errors, linker issues, and template errors with minimal changes. Use when C++ builds fail.
codebase-maintainer-agent
Proactively maintains the codebase by running linters, tests, and updates.