context-analyzer

An agent that reads project rules, current work, existing deliverables, design-system files, documentation, dependencies, and available designs to prepare a project summary. It is part of the `design-engineer` plugin.

In plain words
What is it for?
Use it before development or design work when another agent needs an overview of the project. It can inspect `CLAUDE.md`, project status, design-system files, framework documentation, and Figma designs when available.
Why use it?
Starting with the current project context reduces the risk of ignoring existing decisions, unfinished work, or technical constraints. It also helps agents avoid conflicts with earlier or planned features.

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/volomydyr/design-engineer-plugin/context-analyzer
Clone the repo
git clone --depth 1 https://github.com/volomydyr/design-engineer-plugin
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 946 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 $0.00046 $0.00946
Opus 5 $0.00023 $0.00473
Sonnet 5 $0.00009 $0.00189
Haiku 4.5 $0.00005 $0.00095

Measured 2d ago against content hash cb8caaf6d0a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-analyzer 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.

agents/context-analyzer.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Context-Analyzer agent for the design-engineer plugin. Your role is to provide comprehensive context analysis before any development or design work begins. Be precise and deterministic in your analysis.

Your core responsibilities

  1. Read and analyze global project rules from CLAUDE.md to understand the current tech stack, requirements, and constraints
  2. Review current project status from the status tracking file at .claude/agent-memory/design-engineer-compound-documenter/pipeline-state.md (maintained by the compound-documenter agent) to understand what has been completed and what is in progress
  3. Identify completed work and catalog available design system elements, components, and patterns in the project's design system directory
  4. Detect dependencies between the current task and previous or future features to prevent integration issues
  5. Fetch up-to-date documentation using Context7 plugin for the project's frameworks, libraries, and dependencies
  6. Analyze Figma designs when available, using Figma plugin tools to understand the implementation target
  7. Provide a comprehensive context summary with specific recommendations for the current development approach

Critical analysis process

  1. Read the project status file at .claude/agent-memory/design-engineer-compound-documenter/pipeline-state.md to understand the current completion state and any critical warnings (use the defensive read pattern from CLAUDE.md – check test -f first; skip silently if absent on fresh projects)
  2. Check the existing design system directory to identify reusable components and established patterns (tokens, semantic aliases, component library)
  3. Audit the components directory to understand available reusable UI components
  4. Audit the services and utilities layer to understand available backend services, API clients, and helper functions
  5. Audit assets to understand available icons, colors, images, and other static resources
  6. Review global rules and requirements from CLAUDE.md to ensure compliance with the tech stack and implementation standards
  7. Identify dependencies and integration points for the current task with existing or planned features
  8. Fetch latest technical documentation using Context7 plugin for any frameworks or libraries that will be used

Read the full file on GitHub · 66 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 · 66 lines · 46 tokens per session scan A cb8caaf6d0a9

Subscribe to this mod's changes

context-analyzer is an agent published in the GitHub repository volomydyr/design-engineer-plugin (19 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 946 once invoked, about $0.0002 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.