feature-architect

feature-architect is an agent for Claude Code from rp1-run/rp1. It costs 25 tokens per session (3,856 once invoked), scanned A, original, Apache-2.0.

A technical design agent that turns feature requirements into implementation specifications, including architecture, technology choices, interfaces, and data models. It is used by a build workflow and records uncertain assumptions for the caller.

In plain words
What is it for?
Use it to design a feature's technical approach and identify assumptions that need validation.
Why use it?
It gives developers a structured design before coding begins and encourages reuse of existing project patterns. It keeps design decisions separate from assumption testing.

Agent for Claude Code

Written for Claude Code: arguments in frontmatter. Also seen: model in frontmatter; positional $N argument.

Part of the rp1-dev plugin — 23 skills, 36 agents shipped together

Good fit Use it to design a feature's technical approach and identify assumptions that need validation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rp1-run/rp1/feature-architect
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.

Clone the repo
git clone --depth 1 https://github.com/rp1-run/rp1

Made for: Claude Code.

Or install rp1-dev, the plugin that ships this one along with the rest of its 23 skills, 36 agents.

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 feature-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/rp1-run/rp1/feature-architect/github.svg)](https://agentmods.dev/agents/rp1-run/rp1/feature-architect)
Your own site
<a href="https://agentmods.dev/agents/rp1-run/rp1/feature-architect"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/feature-architect/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for feature-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/rp1-run/rp1/feature-architect"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/feature-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,856 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00025 $0.03856
Opus 5 $0.00013 $0.01928
Sonnet 5 $0.00005 $0.00771
Haiku 4.5 $0.00003 $0.00386

Measured yesterday against content hash a4ae97d69362, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

feature-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 yesterday.

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/dev/agents/feature-architect.md · 431 lines

How it starts

The opening of the file, as written. The whole thing — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Architect Agent

§ROLE: TechDesigner - transforms requirements into technical design. HOW to implement via architecture, tech choices, APIs, data models.

Constraint: Follow existing patterns. Only introduce new if user explicitly requests. Does NOT spawn hypothesis-tester (returns flagged hypotheses for caller).

<feature_id>$1</feature_id> <afk_mode>$2</afk_mode> <update_mode>$3</update_mode> <update_context>{{UPDATE_CONTEXT from prompt}}</update_context> <kb_root>{{KB_ROOT from prompt}}</kb_root> <work_root>{{WORK_ROOT from prompt}}</work_root> <code_root>{{CODE_ROOT from prompt}}</code_root> Feature dir: {WORK_ROOT}/features/{FEATURE_ID}/

Code Root Directive

When CODE_ROOT is non-empty, resolve all source-file exploration (Glob, Read for codebase pattern analysis) against CODE_ROOT. Work artifacts use WORK_ROOT; KB reads use KB_ROOT. When CODE_ROOT is empty, fall back to the current working directory.

§1 KB Loading

{% include_shared "kb-progressive-loading.md" %}

Additional files:

  • {KB_ROOT}/patterns.md - tech patterns, naming, impl patterns
  • {KB_ROOT}/architecture.md - arch patterns, layers, integration

§2 Requirements Loading

Read {WORK_ROOT}/features/{FEATURE_ID}/requirements.md.

Validation: Missing requirements.md -> exit with error JSON:

{"status": "error", "message": "Requirements document required. Run /build Step 1 first."}

§2.1 Oversized Scope Gate

Before design generation, classify whether the requirements still fit a single feature.

Return needs_phase_planning and STOP when the requirements describe:

  • multiple independently valuable child features or work packages
  • explicit sequencing across phases, releases, or rollout slices
  • initiative-sized scope that would require the user to choose between distinct next-step feature handoffs

Do NOT trigger phase planning when the work is broad but still one cohesive feature with one user-facing outcome. Do NOT trigger phase planning from routing provenance alone. Treat ## Planning Traceability, source-artifact references, stable phase IDs, and embedded PHASE_PLAN_PATH=... PHASE_ID=... commands as metadata for the current child slice, not evidence that the requirements still describe multiple phases. If the requirements already contain resolved child-phase provenance, redirect only when the substantive requirements body outside that provenance still describes multiple independently valuable phases, releases, or handoffs.

Read the full file on GitHub · 431 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. yesterday First seen · 431 lines · 25 tokens per session scan A a4ae97d69362

Subscribe to this mod's changes

feature-architect is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed yesterday), licensed Apache-2.0. It adds 25 tokens to every session and 3,856 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 2026-09-07.

Related

Other agents, from other repositories

adversarial-reviewer

Reviews adversarial-authoring drafts.

intent-driven-dev/intent-driven-template · 7 tokens

skill-creator

Generates or modifies optimized skill files. In creation mode, builds from raw user knowledge. In modification mode, applies targeted changes to existing skills while preserving unchanged content. Use when creating new skills or updating existing ones.

shinpr/rashomon · 47 tokens

validator

Read-only adversarial validator. Spawned by scout to verify research findings against the actual code. Challenges assumptions, confirms or refutes claims, and reports CONFIRMED/CONTESTED/UNVERIFIED. Cannot modify files or run commands — enforced by tool restrictions.

justinjdev/fellowship · 56 tokens

dev-agent-ux-designer

Read-only. Turns the architect's specification into an intentional, coherent UI/UX design system -- information architecture, navigation, layouts, typography, color, component hierarchy, and every UI state (loading/empty/error/success). Avoids generic AI-slop interfaces. Never implements application code.

Surjal/dev-agent · 58 tokens

ai-slop-cleaner

Clean AI-generated code anti-patterns — redundant comments, one-use abstractions, over-engineering, template slop — via behavior-preserving edits verified by compile/lint.

RaNDoM6913/claude-code-superkit · 40 tokens

dependency-checker

Audit dependencies across ecosystems — npm audit, govulncheck, pip-audit, cargo-audit, outdated packages, risk categorization, ordered update plan.

RaNDoM6913/claude-code-superkit · 35 tokens