arch-critic
01Agent Claude Code
Independent architecture reviewer that finds design defects before any code exists. Must be a different model family than the Architect.
not rated 27 2d ago A 26 tokens
original MIT
27Stars on the repository
11Mods indexed here, across every type
2d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
architect
02Agent Claude Code
Pragmatic architect that turns a PRD into a concrete technical design favoring simplicity.
not rated 27 2d ago A 20 tokens
original MIT
lead-eng
03Agent Claude Code
Senior engineer that implements features per the architecture and writes open tests.
not rated 27 2d ago A 16 tokens
original MIT
Agent Claude Code
Post-ship analyst that evaluates delivered code against PRD success criteria and KPIs. Runs after merge to verify the build actually achieved its goals.
not rated 27 2d ago A 34 tokens
original MIT
product-mgr
05Agent Claude Code
Crisp PM that turns a raw goal into a tight PRD with Given/When/Then acceptance criteria.
not rated 27 2d ago A 27 tokens
original MIT
qa-sealed
06Agent Claude Code
Paranoid QA that writes behavioral tests from the spec alone — never sees implementation code.
not rated 27 2d ago A 21 tokens
original MIT
qa-validator
07Agent Claude Code
Methodical analyst that runs both test suites and produces the Shadow Score with failure details, in Shadow Score Spec v2.0 conformant markdown + JSON.
not rated 27 2d ago A 34 tokens
original MIT
red-team
08Agent Claude Code
Adversarial security reviewer that attacks the implementation for what the specification forgot. Must be a different model family than the implementer.
not rated 27 2d ago A 29 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: