backend-api
01Agent Claude Code
Server-side services and HTTP/RPC APIs — endpoint design, validation, auth, error contracts, pagination, idempotency, and background work.
not rated 0 1mo ago A 32 tokens
original MIT
Agent Claude Code
Judges whether work is fit to ship — correctness, edge cases, and the failure modes the author was too close to see.
not rated 0 1mo ago A 30 tokens
original MIT
Agent Claude Code
Writes and edits business-facing copy — announcements, help articles, sales and marketing pages, internal comms — in the organisation's own voice.
not rated 0 1mo ago A 31 tokens
original MIT
Agent Claude Code
Resolves customer issues using the organisation's documented policy and product knowledge — triage, troubleshooting, escalation, and replies that hold up.
not rated 0 1mo ago A 30 tokens
original MIT
data-analyst
05Agent Claude Code
Turns business questions into queries, metrics, and honest answers — analysis, dashboards, cohorts, and the caveats that come with them.
not rated 0 1mo ago A 32 tokens
original MIT
database
06Agent Claude Code
Schema design, migrations, indexing, and query performance across SQL and document stores.
not rated 0 1mo ago A 18 tokens
original MIT
docs
07Agent Claude Code
READMEs, API references, architecture notes, changelogs, and inline comments — written for the person who arrives without context.
not rated 0 1mo ago A 29 tokens
original MIT
planner
08Agent Claude Code
Turns an open-ended request into a scoped, ordered plan with the decisions made and the trade-offs named — before anyone writes code.
not rated 0 1mo ago A 28 tokens
original MIT
Agent Claude Code
Maps a manual business process and automates the parts that should be automated — integrations, scheduled jobs, approvals, and the handoffs between them.
not rated 0 1mo ago A 33 tokens
original MIT
Agent Claude Code
Gathers, verifies, and synthesises information — market and competitor scans, vendor evaluations, background briefs — with every claim traceable to a source.
not rated 0 1mo ago A 35 tokens
original MIT
security
11Agent Claude Code
Defensive security — reviewing code for vulnerabilities, hardening authentication and authorisation, secrets handling, dependency and input-handling risk.
not rated 0 1mo ago A 28 tokens
original MIT
testing
12Agent Claude Code
Test strategy and implementation — unit, integration, and end-to-end suites, fixtures, flake elimination, and coverage that means something.
not rated 0 1mo ago A 29 tokens
original MIT
Agent Claude Code
Interface design and implementation — Material 3 (Expressive) on Android/web and Apple's Liquid Glass on iOS/macOS, plus layout, motion, and accessibility.
not rated 0 1mo ago A 38 tokens
original MIT
MCP server Claude CodeCodexCursor +2
MCP server that decides how much delegation a task deserves, routes it to specialist agents (single or planner-executor-tester-reviewer pipeline), and remembers how your business wants work done. Runs locally from the fushiguro-mcp npm package.
not rated 0 1mo ago A
tokens not measured
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: