Agent Claude Code
Produces images + SVG via the fallback chain. Matches the locked palette, degrades gracefully, never fakes assets.
not rated 34 yesterday A 27 tokens
original Apache-2.0
34Stars on the repository
19Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown
Agent Claude Code
Independent anti-slop reviewer. Runs the deterministic detectors + taste pre-flight, logs every violation, edits nothing.
not rated 34 yesterday A 26 tokens
original Apache-2.0
designer
03Agent Claude Code
Master UI/UX designer-developer. Builds one surface to the chosen authority + dials, sources real assets, never self-approves.
not rated 34 yesterday A 31 tokens
original Apache-2.0
trend-scout
04Agent Claude Code
Researches the current trend lane for a design kind. Read-only web research, records dated findings, recommends one lane.
not rated 34 yesterday A 28 tokens
original Apache-2.0
Agent Claude Code
Optional Critic — independent reviewer who re-reads request/docs, surfaces required behaviors the existing tests miss, and writes NEW FAILING tests for them. Also flags correctness/test/style defects. Never edits src; never weakens existing tests.
not rated 34 yesterday A 51 tokens
original Apache-2.0
db-reader
06Agent Claude Code
Read-only, DB-independent data reader for supergoal evidence - fetches test auth, source-of-truth expected values, schema metadata, and dataset/environment diffs over MySQL/PostgreSQL/SQLite. Returns small named values + diffs, never raw rows or secrets. Issues SELECT-class statements only; never writes.
not rated 34 yesterday A 67 tokens
original Apache-2.0
debugger
07Agent Claude Code
DEBUG-mode root-cause analyst — reproduces the failure, runs hypothesis-driven diagnosis to one confirmed cause, and writes a minimal-fix plan. Alt persona for deep causal tracing — tracer.
not rated 34 yesterday A 41 tokens
original Apache-2.0
executor
08Agent Claude Code
Builder/Improver/Fixer — implements the smallest correct change for Build, full-spec improve, edge-case improve, or a failing test. As Fixer never edits test files. Never approves its own work.
not rated 34 yesterday A 44 tokens
original Apache-2.0
explore
09Agent Claude Code
Codebase mapping specialist — maps the code a change touches with file:line evidence. Read-only; never edits source.
not rated 34 yesterday A 27 tokens
original Apache-2.0
qa-auditor
10Agent Claude Code
QA-ONLY app driver — exercises a running app with playwright-cli (native sessions/state/CDP-attach for authenticated logins) through user scenarios and comparisons (functional/data-integrity/before-after/A-B/env), within an action cap, recording human + machine evidence. Reads no DB directly (the db-reader subagent…
not rated 34 yesterday A 77 tokens
original Apache-2.0
qa-tester
11Agent Claude Code
Black-box QA — drives the running app with playwright-cli through golden, edge, and a11y flows and records as-is/to-be evidence. Distinct from Verify, which re-runs the real tests with no browser.
not rated 34 yesterday A 49 tokens
original Apache-2.0
Agent Claude Code
Verify-phase security reviewer — OWASP, secrets, injection, SSRF, unsafe crypto. Findings only; never edits source.
not rated 34 yesterday A 29 tokens
original Apache-2.0
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: