What it does
The agent studies how similar features are already built in a codebase, then returns a blueprint. The blueprint names the specific files to create or modify, describes the components and their responsibilities, traces the data flow, and sets out a phased build sequence. The output is meant to be a concrete plan rather than a set of options.
It suits the point where a new feature has to fit established conventions and the team wants a plan first. A vague request such as "add saved searches, but I'm not sure where it should live" is one example. The publisher contrasts it with tasks that explain an existing feature, which suit a different agent, and with designing a service from scratch.
The publisher's material does not list setup steps, runtime requirements or the form in which the agent is invoked. Its examples show it being asked for a design on a codebase it can read, and the blueprint is produced from that analysis.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 18 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 1536
code-architect
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences. Use PROACTIVELY when a new feature needs to be designed on top of an existing codebase, before any implementation code is written. <example> Context: A team needs to add a notifications feature to an existing SaaS product and wants a concrete plan before writing code. user: "We need to add in-app notifications to our dashboard. Can you design how this should fit in
As shown on www.aitmpl.com when we last read it