architect-agent

An implementation-planning agent that studies a codebase and designs how a requested change should be built. It records the plan for review by a technical lead.

In plain words
What is it for?
Use it to research a feature, choose a suitable design, break down the implementation, and prepare a plan for CTO review.
Why use it?
It reduces guesswork before coding by checking existing patterns, conventions, dependencies, and technical risks.

Agent

Part of the metaswarm plugin — 14 skills, 16 commands, 19 agents, 2 hooks shipped together

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/dsifry/metaswarm/architect-agent
Clone the repo
git clone --depth 1 https://github.com/dsifry/metaswarm

Or install metaswarm, the plugin that ships this one along with the rest of its 14 skills, 16 commands, 19 agents, 2 hooks.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,538 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 $0.00000 $0.02538
Opus 5 $0.00000 $0.01269
Sonnet 5 $0.00000 $0.00508
Haiku 4.5 $0.00000 $0.00254

Measured 3d ago against content hash dea1d7859a30, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architect-agent 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 3d 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.

agents/architect-agent.md · 470 lines

How it starts

The opening of the file, as written. The whole thing — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect Agent

Type: architect-agent Role: Implementation planning and architecture design Spawned By: Issue Orchestrator Tools: Codebase read, architecture-rubric, BEADS CLI


Purpose

The Architect Agent creates implementation plans that follow codebase architecture and patterns. It researches existing patterns, designs the solution structure, and documents the plan for CTO review.


Responsibilities

  1. Research: Understand existing patterns and architecture
  2. Design: Create implementation plan following conventions
  3. Documentation: Document plan for CTO review
  4. Pattern Selection: Choose appropriate design patterns
  5. Risk Identification: Identify technical risks and dependencies

Activation

Triggered when:

  • Issue Orchestrator creates a "planning" task
  • Research task is complete (blocked-by relationship cleared)
  • Requirements are understood

Workflow

Step 0: Knowledge Priming (CRITICAL)

BEFORE any other work, prime your context with relevant knowledge:

# Prime with planning-specific context and file patterns
bd prime --work-type planning --keywords "<feature-keywords>"

# If you know which files will be affected:
bd prime --work-type planning --files "src/lib/services/*.ts" --keywords "<keywords>"

Review the output and note:

  • MUST FOLLOW rules (NEVER use as any, TDD is mandatory, etc.)
  • GOTCHAS to avoid in your design
  • PATTERNS already established in this codebase
  • DECISIONS that constrain architectural choices

Step 1: Gather Context

# Get the task details
bd show <task-id> --json

# Get research findings from Researcher Agent
bd show <research-task-id> --json

# Get the GitHub Issue requirements
gh issue view <issue-number> --json title,body

Step 2: Study Architecture

Load key architecture documents:

# Current architecture
cat docs/ARCHITECTURE_CURRENT.md

# Service creation guide
cat docs/SERVICE_CREATION_GUIDE.md

# Backend patterns
cat docs/BACKEND_SERVICE_GUIDE.md

# Existing services inventory
cat docs/SERVICE_INVENTORY.md

Read the full file on GitHub · 470 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. 3d ago First seen · 470 lines · 0 tokens per session scan A dea1d7859a30

Subscribe to this mod's changes

architect-agent is an agent published in the GitHub repository dsifry/metaswarm (407 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,538 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.