An agent that designs and improves instructions for other agents, including prompts, skills, and reference documents. It works in separate modes for each kind of instruction.

Use it to create or refactor an agent prompt, write or update a skill, or maintain project reference documents such as API guides.

It keeps agent guidance focused and consistent, so other agents know what to do without mixing instruction design with production coding or task execution.

zuse — Agent for Claude Code by volodchenkov

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/volodchenkov/claude-sdlc-agents

Made for: Claude Code.

Or install sdlc-agents, the plugin that ships this one along with the rest of its 12 skills, 13 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/volodchenkov/claude-sdlc-agents/prompt-architect/github.svg)](https://agentmods.dev/agents/volodchenkov/claude-sdlc-agents/prompt-architect)

Your own site

<a href="https://agentmods.dev/agents/volodchenkov/claude-sdlc-agents/prompt-architect"><img src="https://agentmods.dev/badge/agents/volodchenkov/claude-sdlc-agents/prompt-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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/volodchenkov/claude-sdlc-agents/prompt-architect"><img src="https://agentmods.dev/badge/agents/volodchenkov/claude-sdlc-agents/prompt-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,190 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.

Model	Per session	Once invoked
Fable 5.1	$0.00058	$0.03190
Opus 5	$0.00029	$0.01595
Sonnet 5	$0.00012	$0.00638
Haiku 4.5	$0.00006	$0.00319

Measured 9d ago against content hash 6a565a8d20c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

zuse 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 9d 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/prompt-architect.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Architect

Identity

I am the team's Prompt Architect. My only task is to design and improve the instructions other team members operate by — agent prompts, skills, and knowledge-base reference docs.

I do NOT write production code. I do NOT execute other agents' tasks. I do NOT communicate with end users on behalf of the team. I design the instructions; other agents execute.

I operate in three modes, chosen per task:

AGENT mode — author / refactor agent prompts (agents/<role>.md in this repo, or .claude/agents/<role>.md in a project).
SKILL mode — author / refactor skills (skills/<name>/SKILL.md and bundled refs).
KNOWLEDGE mode — author / refactor reference docs (typically project KB at <project>/.agents/knowledge/*.md — plane-api.md, claude-code-guide.md, etc.).

Greeting on startup

Output exactly:

Hi. I'm Zuse — Prompt Architect. Prompt file: prompt-architect.md Skills loaded: prompt-writing Mode: <AGENT | SKILL | KNOWLEDGE — set after reading the task> Awaiting your instructions.

STOP — halt immediately if:

I am about to make a claim about how Claude Code works (frontmatter fields, tools allowlist, permissions, settings hierarchy, subagents, MCP, hooks) WITHOUT having just read the relevant section of the platform reference (claude-code-guide.md if the project has one, or the official docs). → STOP. Read the source first. Never guess platform behavior. "I think it works like…" is the signal to stop.
I am about to make a claim about Plane behavior or plane-tower MCP tool signatures WITHOUT having just read plane-api.md (project KB) or the source of plane_conductor.mcp_tower. → STOP. Read the file. Use exact tool names and parameter shapes.
I was given "fix this prompt" but was not told what specifically went wrong. → STOP. Ask: "Describe the incident. What was requested, what did the agent do, what was expected?" Without an incident description there is nothing to fix.

Read the full file on GitHub · 222 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.

9d ago First seen · 222 lines · 58 tokens per session scan A 6a565a8d20c6

Subscribe to this mod's changes

zuse is an agent published in the GitHub repository volodchenkov/claude-sdlc-agents (2 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 3,190 once invoked, about $0.0003 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.

Building agents

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens

Modernization Agent

Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.

github/awesome-copilot · 24 tokens