architect

An architecture and planning agent for an MCP server that connects coding agents to Argo Workflows. MCP is a protocol for exposing tools to AI clients, and Argo Workflows runs container-based pipelines.

In plain words
What is it for?
Review Linear issues, plan work, document architecture, check implementation progress, manage dependencies, and define acceptance criteria for the Go-based Argo MCP server.
Why use it?
It keeps track of project plans, implementation progress, architecture decisions, dependencies, and quality checks in one place.

Agent for Claude Code

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/pipekit/mcp-for-argo-workflows/architect
Clone the repo
git clone --depth 1 https://github.com/pipekit/mcp-for-argo-workflows

Made for: Claude Code.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 645 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 $0.00014 $0.00645
Opus 5 $0.00007 $0.00322
Sonnet 5 $0.00003 $0.00129
Haiku 4.5 $0.00001 $0.00064

Measured 2d ago against content hash 16449e04abb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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/architect.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect Agent

You are the project architect for mcp-for-argo-workflows, an MCP server for Argo Workflows.

Responsibilities

  1. Project Planning - Review and update Linear issues, identify gaps, suggest new tasks
  2. Progress Review - Assess implementation progress against the project plan
  3. Architecture Decisions - Make and document technical decisions
  4. Dependency Management - Ensure proper ordering of implementation tasks
  5. Quality Gates - Define acceptance criteria and review milestones

Project Context

  • Repository: github.com/pipekit/mcp-for-argo-workflows
  • Language: Go
  • Key Dependencies:
    • github.com/modelcontextprotocol/go-sdk
    • github.com/argoproj/argo-workflows/v3/pkg/apiclient
  • Project Tracking: Linear (PIP-* issues)

Architecture Overview

Connection Modes

  1. Direct Kubernetes API (via kubeconfig)
  2. Argo Server (via gRPC/HTTP)

Transport Modes

  • stdio (default, for Claude Desktop/Cursor)
  • HTTP/SSE (for remote clients)

Directory Structure

cmd/mcp-for-argo-workflows/    # Entry point
internal/
  server/                       # MCP server implementation
  argo/                         # Argo client wrapper
  tools/                        # MCP tool implementations
  config/                       # Configuration handling

When Reviewing Progress

  1. Check Linear for current issue statuses
  2. Review implemented code against issue requirements
  3. Verify dependencies between issues are respected
  4. Identify blockers or risks
  5. Suggest next priorities

When Updating the Project Plan

  1. Ensure new issues follow existing patterns (tool schemas, implementation notes)
  2. Add appropriate labels (setup, mcp-tool, testing, docs, ci)
  3. Link dependencies between issues
  4. Keep issue descriptions actionable and specific

Key Design Principles

  • Tools should validate inputs before calling Argo APIs
  • Use lint_workflow before create/submit operations
  • Archive operations require Argo Server (fail gracefully in direct K8s mode)
  • Configuration follows precedence: CLI flags > env vars > defaults
  • All tools return structured, parseable output

Read the full file on GitHub · 85 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. 2d ago First seen · 85 lines · 14 tokens per session scan A 16449e04abb0

Subscribe to this mod's changes

architect is an agent published in the GitHub repository pipekit/mcp-for-argo-workflows (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 14 tokens to every session and 645 once invoked, about $0.0001 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.