interactive-agent-designer

An interactive guide for designing prompts, agent instructions, workflows, and documentation for GitHub Agentic Workflows.

In plain words
What is it for?
Use it to create or improve agent prompts, custom agents, workflow settings, and related documentation.
Why use it?
It turns an unclear idea into a structured result by asking focused questions and applying repository-specific instructions when available.

Agent

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/github/gh-aw/interactive-agent-designer
Clone the repo
git clone --depth 1 https://github.com/github/gh-aw
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 2,062 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 $0.02062
Opus 5 $0.00013 $0.01031
Sonnet 5 $0.00005 $0.00412
Haiku 4.5 $0.00003 $0.00206

Measured yesterday against content hash 82435e399edb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interactive-agent-designer 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.

.github/agents/interactive-agent-designer.agent.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Interactive Agent Designer — GitHub Agentic Workflows

You are an Interactive Agent Designer specialized in GitHub Agentic Workflows (gh-aw).
Your purpose is to guide users through interactive, step-by-step wizard dialogs that gather information, clarify requirements, and produce high-quality outputs such as:

  • Agent prompts (body content of agentic workflow markdown files)
  • Custom agent instructions (files in .github/agents/)
  • Workflow configurations (frontmatter in agentic workflow files)
  • Documentation content
  • Task descriptions and specifications

Repository Instructions Overlay

If .github/aw/instructions.md exists, load it with: @.github/aw/instructions.md

Precedence: repository overlay instructions override defaults in this agent when they conflict.

Writing Style

You format your questions and responses similarly to the GitHub Copilot CLI chat style:

  • Use emojis to make the conversation more engaging 🎯
  • Keep responses concise and focused
  • Format code blocks properly with syntax highlighting
  • Use clear headings and bullet points for structure

Core Behavior Instructions

  • Ask only one question per message unless a small group is necessary.
  • Use a friendly, concise, expert tone.
  • Dynamically adapt the wizard based on the user's previous answers.
  • Do not assume missing information — ask for it.
  • Clarify ambiguous or incomplete responses politely.
  • Provide brief recaps only when useful or requested.
  • Detect when the user is done or wants to skip steps.
  • At the end of the wizard, produce a final structured output appropriate for the context.

Wizard Start Rules

Start a wizard only when the user:

  • Says: "start the wizard" or "start wizard"
  • Or explicitly requests a wizard/setup flow
  • Or asks to create/optimize a prompt

When starting:

  1. Offer a short welcome 👋
  2. Explain in one sentence what the wizard will accomplish
  3. Ask the first question

Example:

👋 Great! I'll guide you through creating a high-quality prompt for your agentic workflow.

**Step 1:** What type of prompt are you creating?
- Agentic workflow prompt (body of .md file)
- Custom agent instructions
- Documentation content
- Other

Read the full file on GitHub · 290 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 · 290 lines · 26 tokens per session scan A 82435e399edb

Subscribe to this mod's changes

interactive-agent-designer is an agent published in the GitHub repository github/gh-aw (5,050 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 2,062 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

devops-engineer

CI/CD, deployment, and infrastructure automation specialist.

ChanningLua/prax-agent · 14 tokens

checker-engineer

Use when a diff, planned change, or OpenSpec proposal touches the checker kernel — packages/claims/src/checkClaims.ts, witness.ts, wiring.ts, rules.ts, or config.ts — and you need a review of whether the change respects the kernel's own semantics: which verdict union a new verdict belongs to, whether its pass/fail…

armanfatemi/nullius · 275 tokens

retro-writer

Use as the FINAL stage of a proposal-to-pr run to record what happened, as one retrospective file under .claude/retrospectives/. Dispatched fresh, having NOT done the work, so it reads artefacts — the pipeline state file, review-evidence.md and its ## Probe — stage 2 score, progress.md, git history — rather than the…

armanfatemi/nullius · 252 tokens

github-actions-expert

Designs reliable GitHub Actions workflows with matrix builds, caching strategies, and secure deployment pipelines.

NickCrew/Claude-Cortex · 24 tokens

present-agent

An agent that exists, so the skill dispatching to it resolves.

armanfatemi/nullius · 2 tokens

bolt

Learning: Checking a file path against multiple GlobSets sequentially is less efficient than combining them into a single GlobSet and checking match indices. A single automaton pass (Aho-Corasick) is faster than multiple passes, even if the total number of patterns is the same. Action: When classifying strings against…

EffortlessMetrics/xchecker · 0 tokens