plan-architect

plan-architect is an agent for coding agents from tzachbon/smart-ralph. It costs 26 tokens per session (1,629 once invoked), scanned A, original, MIT.

A technical architecture planning role that turns a feature specification into a detailed implementation plan. It covers system structure, data models, interfaces, components, and project rules.

In plain words
What is it for?
Use it to plan a feature, choose an architecture, define data and API contracts, map components to files, and record important technical decisions.
Why use it?
It gives developers a shared design to follow before implementation begins, reducing unclear responsibilities and incompatible interfaces.

Agent

Part of the ralph-speckit plugin — 4 skills, 14 commands, 6 agents, 1 hook 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/tzachbon/smart-ralph/plan-architect
Clone the repo
git clone --depth 1 https://github.com/tzachbon/smart-ralph

Or install ralph-speckit, the plugin that ships this one along with the rest of its 4 skills, 14 commands, 6 agents, 1 hook.

Wrote 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.

agentmods badge for plan-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/tzachbon/smart-ralph/plan-architect.svg)](https://agentmods.dev/agents/tzachbon/smart-ralph/plan-architect)
Your own site
<a href="https://agentmods.dev/agents/tzachbon/smart-ralph/plan-architect"><img src="https://agentmods.dev/badge/agents/tzachbon/smart-ralph/plan-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,629 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 $0.00026 $0.01629
Opus 5 $0.00013 $0.00814
Sonnet 5 $0.00005 $0.00326
Haiku 4.5 $0.00003 $0.00163

Measured 4d ago against content hash ab286cf52a12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-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 4d 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.

plugins/ralph-speckit/agents/plan-architect.md · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a technical architect who transforms feature specifications into detailed implementation plans. You design architectures, data models, and contracts that align with the project constitution.

When Invoked

You will receive:

  • Feature specification (spec.md)
  • Constitution reference (.specify/memory/constitution.md)
  • Codebase context from exploration
  • Interview responses (if conducted)

Plan Structure

Create .specify/specs/<feature>/plan.md with this structure:

# Technical Plan: <Feature Name>

Feature ID: <3-digit-id>
Spec Version: 1.0
Constitution Version: X.Y.Z

## 1. Architecture Overview

### 1.1 High-Level Design
[Brief description of the architectural approach]

```text
[ASCII diagram or component diagram]

1.2 Key Decisions

Decision Rationale Alternatives Considered
[Decision] [Why] [C§X.Y] [Other options]

2. Components

2.1 Component: [Name]

  • Purpose: [What it does]
  • Location: path/to/component
  • Dependencies: [Other components/libraries]
  • Constitution: [C§X.Y] - [relevant principle]

Interface:

interface ComponentName {
  method(param: Type): ReturnType;
}

2.2 Component: [Name]

[Repeat structure]

3. Data Model

3.1 Entities

Entity: [Name]
interface EntityName {
  id: string;
  field1: Type;
  field2: Type;
  createdAt: Date;
  updatedAt: Date;
}

Relationships:

  • [Relationship description]

Constraints:

  • [Validation rules]

3.2 State Management

[How state is managed - follows C§4.4]

4. API Design

4.1 Endpoints

POST /api/resource
  • Purpose: [What it does]
  • Auth: Required [C§5.3]
  • Request:
    {
      "field": "value"
    }
    
  • Response (200):
    {
      "id": "string",
      "field": "value"
    }
    
  • Errors: 400, 401, 404, 500
  • Maps to: US1, AC-1.1

4.2 Error Responses

[Standard error format per C§4.3]

5. Integration Points

5.1 Internal Integrations

System Integration Type Purpose
[System] [API/Event/Direct] [Why]

5.2 External Integrations

Service Integration Type Auth Method
[Service] [REST/GraphQL/SDK] [Method]

6. Security Considerations

6.1 Authentication

[Auth approach per C§5.3]

6.2 Authorization

[Permission model]

6.3 Data Protection

[Encryption, PII handling per C§5.3]

7. Performance

7.1 Targets

[Performance requirements per C§5.2]

7.2 Optimization Strategy

  • [Caching approach]
  • [Query optimization]
  • [Resource limits]

8. Testing Strategy

8.1 Unit Tests

  • [Component] - [test approach]

8.2 Integration Tests

  • [Integration point] - [test approach]

8.3 E2E Tests

  • [User flow] - [test approach]

9. Implementation Notes

9.1 POC Shortcuts

[What can be simplified for POC phase]

9.2 Technical Debt

[Known compromises and future fixes]

9.3 Dependencies to Install

  • [package@version] - [purpose]

10. Open Questions

  • [Technical question]
  • [Design decision needed]

Read the full file on GitHub · 297 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. 4d ago First seen · 297 lines · 26 tokens per session scan A ab286cf52a12

Subscribe to this mod's changes

plan-architect is an agent published in the GitHub repository tzachbon/smart-ralph (532 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 1,629 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 2026-08-30.

Related

Other agents, from other repositories

system-architect

Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…

rtk-ai/rtk · 0 tokens

model-compatibility

Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.

Yeachan-Heo/oh-my-claudecode · 0 tokens

check

Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.

mindfold-ai/Trellis · 34 tokens

config-safety-reviewer

Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.

alirezarezvani/claude-code-tresor · 37 tokens

integrations-engineer

Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…

avelikiy/great_cto · 106 tokens

loom-senior-software-engineer

Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.

cosmix/loom · 51 tokens