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/1mcp-app/agent/architecture-opportunitiesgit clone --depth 1 https://github.com/1mcp-app/agentWrote 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/1mcp-app/agent/architecture-opportunities)<a href="https://agentmods.dev/agents/1mcp-app/agent/architecture-opportunities"><img src="https://agentmods.dev/badge/agents/1mcp-app/agent/architecture-opportunities.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 | $0.00000 | $0.14979 |
| Opus 5 | $0.00000 | $0.07489 |
| Sonnet 5 | $0.00000 | $0.02996 |
| Haiku 4.5 | $0.00000 | $0.01498 |
Grade A, and why
architecture-opportunities 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 — 518 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Deepening Opportunities
This note records the architecture review from 2026-05-08. It is an agent-facing worklist for future refactors, not public product documentation.
Current Codebase Status
Last checked against the working tree on 2026-05-27.
- Milestone 1 is implemented:
templateIdentity.tsandrequestContextPreparation.tsexist, with targeted inspect and REST tool routes using the shared preparation path. - Milestone 2 is closed for the planned scope:
filterSelection.tsandcapabilityCatalog.tsown selection, visibility, and refresh intent for the migrated HTTP, direct MCP, and notification paths.MetaToolProvider,/api/tools,/api/tool-invocations, direct MCP list handling, and config/async notifications use those seams. - Milestone 3 is closed for the planned scope:
config-change/configChange.tsandinstallation/serverInstallationWorkflow.tsown the migrated mutation and install flows.mcp uninstall, internal remove/uninstall,mcp install, andmcp_installuse those modules; the remaining compatibility facade is intentionally limited to workflows outside this slice. - Milestone 4 is implemented:
streamableSessionLifecycle.tsowns Streamable HTTP creation, lookup, restoration, initialize recovery, and cleanup. The deprecatedsessionService.tscompatibility wrapper has been removed. - Milestone 5 is implemented for
run,inspect,instructions, andproxy:clientSurfaceAttachment.tsowns shared attach-only runtime discovery, auth-profile lookup, Request Context construction, context hash, reusable-session cache behavior forrun/inspect/instructions, REST/MCP fallback classification, stale-session retry, and fresh-session attachment forproxy. - Milestone 6 is complete:
oauthAuthorizationFlow.tsowns consent approval/denial, localhost CLI-token creation, backend OAuth dashboard fact shaping, backend OAuth start/restart, and backend OAuth callback completion/loading-ready notification. HTTP routes delegate OAuth consent, authorization, restart, callback, and CLI-token decisions through structured flow operations while retaining consent/dashboard HTML rendering and HTTP response mapping.instructionsDistribution.tsowns eager-inspection policy, instruction detail collection/assembly, managed startup-doc content, startup-reference rendering, and legacy managed-reference cleanup.instructionsuses its own reusable Client Surface Attachment identity while delegating distribution policy;cli-setupdelegates managed-doc and startup-reference policy while retaining hooks, path resolution, JSON merging, and file writes.
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 · 518 lines · 0 tokens per session scan A d941aa156d5c
architecture-opportunities is an agent published in the GitHub repository 1mcp-app/agent (498 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 14,979 tokens. 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.
Other agents, from other repositories
mobile-developer
Use this agent when building cross-platform mobile applications requiring native performance optimization, platform-specific features, and offline-first architecture. Use for React Native and Flutter projects where code sharing must exceed 80% while maintaining iOS and Android native excellence.
rails-expert
Use when building or modernizing Rails applications requiring API development, Hotwire reactivity, real-time features, background job processing, deployment automation, or Rails-idiomatic patterns for maximum productivity. Version-aware: adapts to Rails 7.x and 8.x projects.
react-frontend-engineer
React frontend engineer for Arthur MCP. Use when implementing, debugging, refactoring, or testing React/TypeScript frontend features, including Feature-Driven Architecture, Atomic Design, barrel exports, pages, components, hooks, state, routing, forms, API integration, i18n, performance, accessibility, and frontend…
expo-react-native-expert
Use when building mobile applications with Expo and React Native that require native module integration, navigation setup, performant animations, push notifications, OTA updates, or App Store/Play Store deployment.
frontend-test-engineer
Frontend test engineer for Arthur MCP. Use when writing, reviewing, debugging, or improving frontend tests for React pages, feature components, hooks, API client behavior, routing, permissions, i18n, forms, and user-visible flows with Vitest and React Testing Library.
license-engineer
Use this agent when architecting, implementing, or optimizing end-to-end legal licensing systems—from OSI standard selection and dependency compliance pipelines to proprietary deployment and risk monitoring.