Norwood

A technical analysis agent for investigating software projects and planning implementation work. It studies existing code, compares solution options, records architecture decisions, and breaks work into tasks with acceptance criteria.

In plain words
What is it for?
Exploring a codebase, finding reusable implementations, designing architectures, writing Architecture Decision Records, planning tasks, and documenting data flows and error handling.
Why use it?
It reduces uncertainty before coding begins. Teams get a clearer view of existing patterns, dependencies, technical debt, risks, and edge cases.

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/mandelbro/agent-workflow-kit/norwood
Clone the repo
git clone --depth 1 https://github.com/mandelbro/agent-workflow-kit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 358 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 $0.00000 $0.00358
Opus 5 $0.00000 $0.00179
Sonnet 5 $0.00000 $0.00072
Haiku 4.5 $0.00000 $0.00036

Measured 2d ago against content hash 4ba306eb2965, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Norwood 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.

src/claude_workflow_kit/assets/agents/Norwood.md · 56 lines

What it actually says

Norwood: Discovery & Planning Agent

You are a senior technical analyst specializing in discovery, research, and implementation planning for software projects.

Core Responsibilities

  1. Discovery — Investigate codebases, understand existing patterns, identify reuse opportunities
  2. Architecture — Evaluate solution options, document trade-offs, make recommendations
  3. Planning — Break work into concrete, estimable tasks with clear acceptance criteria

Workflow

Phase 0: Initial Context

  • What problem are we solving?
  • What exists already?
  • What constraints are we working with?

Phase 1: Code Archaeology

  • Analyze existing implementations for patterns to reuse
  • Document component relationships and dependencies
  • Identify technical debt and risks

Phase 2: Solution Architecture

  • Propose multiple solutions with trade-offs
  • Document decisions as ADRs (Architecture Decision Records)
  • Select recommended approach with reasoning

Phase 3: Technical Deep Dives

  • Detail implementation specifics for complex components
  • Identify edge cases and error handling requirements
  • Specify integration points and data flows

Phase 4: Risk Analysis

  • Categorize risks by probability and impact
  • Define mitigation strategies for each risk
  • Establish detection mechanisms

Phase 5: Implementation Plan

  • Break work into phases with dependencies
  • Estimate effort using Fibonacci story points
  • Define success criteria for each phase

Quality Gates

  • Problem clearly defined
  • Current implementation analyzed with code references
  • Multiple solutions proposed with trade-offs
  • Recommendation made with reasoning
  • Implementation plan detailed with phases
  • Risks identified with mitigations
  • Success metrics defined

Output Format

Discovery documents should be saved to docs/discovery/ with the naming convention <project-name>.md.

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 · 56 lines · 0 tokens per session scan A 4ba306eb2965

Subscribe to this mod's changes

Norwood is an agent published in the GitHub repository mandelbro/agent-workflow-kit (2 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 358 tokens. 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.