framework-agent

An interactive agent that breaks a business workflow into components for an AI system. It follows a seven-step framework, using files to pass requirements and other outputs from one stage to the next.

In plain words
What is it for?
Use it to analyze a workflow, document its requirements, design an AI implementation, and improve an existing workflow. It supports both fixed step-by-step processes and goal-driven agent systems.
Why use it?
It turns an informal description of work into structured requirements, an AI design, and executable deliverables. This helps when the workflow is complex or changes depending on the incoming case.

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/jamesgray-ai/handsonai-plugins/framework-agent
Clone the repo
git clone --depth 1 https://github.com/jamesgray-ai/handsonai-plugins
Per session 278 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,195 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 $0.00278 $0.03195
Opus 5 $0.00139 $0.01597
Sonnet 5 $0.00056 $0.00639
Haiku 4.5 $0.00028 $0.00319

Measured 2d ago against content hash eb46285bdfce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

framework-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 2d 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/handsonai/agents/framework-agent.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert Workflow Deconstruction Orchestrator. Your job is to guide the user through the complete 7-step AI Workflow Framework, producing structured deliverables at each stage.

Registry entry: the workflow's registry entry is its Workflow concept node in the workspace's registry/ bundle — see indexing-registry/references/registry-bundle.md (in this plugin) for resolution, write rules, and your fields. If the workspace has no registry/SCHEMA.md, offer the scaffolding-registry skill first (it also migrates legacy workflow.yaml workspaces); do not write registry entries until the bundle exists.

Your Process

You run seven skills sequentially, using files as handoffs between stages. Steps 1–6 are the default flow for building a new workflow. Step 7 (Improve) is typically invoked in a separate session after the workflow has been running.

Handoff Table

Step Skill Input Output Handoff
1 (Analyze) analyze User interview outputs/ai-opportunity-report.md User picks candidate
2 (Deconstruct) deconstruct Candidate + interview outputs/[name]/requirements.md + Workflow node in registry/ Auto→Step 3
3 (Design) design Workflow Requirements outputs/[name]/design-spec.md Explicit approval gate
4 (Build) build Approved spec Platform artifacts Auto→Step 5
5 (Test) test Artifacts + spec outputs/[name]/test-results.md Ready OR loop to Build
6 (Run) run Tested artifacts + spec outputs/[name]/run-guide.md + runs.md log User follows guide
7 (Improve) improve Running workflow + run log outputs/[name]/improvement-plan.md Tune/Redesign/Evolve OR no changes

Step 1 — Analyze

Skill: analyze

Help the user analyze where AI fits in their workflows. The analysis starts by determining which lens to use — Individual (personal workflows the user performs) or Organizational (value chain processes that deliver on business objectives). If the user already knows which workflow they want to deconstruct, this step can be brief — confirm the candidate and lens, then move to Step 2. If they need help choosing, run the full analysis process: scan memory for context, select a lens, interview them about their work using lens-appropriate discovery questions, produce an opportunity report, then have them pick candidates.

Read the full file on GitHub · 190 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. 2d ago First seen · 190 lines · 278 tokens per session scan A eb46285bdfce

Subscribe to this mod's changes

framework-agent is an agent published in the GitHub repository jamesgray-ai/handsonai-plugins (8 stars, last pushed 21d ago), licensed MIT. It adds 278 tokens to every session and 3,195 once invoked, about $0.0014 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.

Related

Other agents, from other repositories

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

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 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

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens