backend-dev
01Agent
Backend engineer. Handles code changes, backend tests, database migrations, and commits. Use for any backend-only work.
1 2d ago A 26 tokens
original MIT
1Stars on the repository
50Mods indexed here, across every type
2d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Agent
Use this agent when you need to review code for adherence to project guidelines, style guides, and best practices. Use when asked, or after completing a multi-file coding task, especially before committing changes or creating pull requests. Invoke it deliberately; it does not fire automatically on every edit. It will…
1 2d ago A 453 tokens
original MIT
Agent
Use this agent when code has been written or modified and needs to be simplified for clarity, consistency, and maintainability while preserving all functionality. Use when asked, or deliberately after completing a multi-file coding task, it does not fire automatically on every change. It simplifies code by following…
1 2d ago A 447 tokens
original MIT
frontend-dev
04Agent
Frontend engineer. Handles UI code changes, component development, lint/build verification, and commits. Use for any frontend-only work.
1 2d ago A 28 tokens
original MIT
Agent
Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n \nContext: A developer has just created a pull request with new…
1 2d ago A 350 tokens
copy · 81% MIT
qa
06Agent
QA engineer. Runs tests, lint, and build checks. Validates PRs before merge. Reports failures to team lead. Does NOT modify code.
1 2d ago A 32 tokens
original MIT
Agent
For a decision (not code), create an agent team whose members hold distinct personas, skeptic, customer, competitor, domain expert, have each research independently, then make them debate until they reach consensus or name their core disagreement.
1 2d ago A 0 tokens
original MIT
Agent
File conflicts between agents are the primary failure mode of agent teams; design team roles around domain isolation, not component ownership.
1 2d ago A 0 tokens
original MIT
Agent
Teams enable agent-to-agent messaging; they cost 4-7x more tokens than a single session, reserve for genuinely collaborative multi-domain work.
1 2d ago A 0 tokens
original MIT
Agent
Claude Code removed the interactive /agents wizard; create or edit subagents by writing files in .claude/agents/ directly or by asking Claude to do it.
1 2d ago A 0 tokens
original MIT
Agent
Naming subagents 'designer' / 'backend' / 'tester' creates coordination overhead via the main agent; use agent teams for multi-role work instead.
1 2d ago A 0 tokens
original MIT
Agent
TL;DR: When building CLI tools that Claude Code will drive, design the --help text to be self-contained so the agent can learn the whole tool from running it.
1 2d ago A 0 tokens
original MIT
Agent
A subagent that hasn't seen your existing code generates more distinct designs; the main session's code context biases toward what already exists.
1 2d ago A 0 tokens
original MIT
Agent
Forked subagents inherit the full conversation history (and share its prompt cache), so they preserve nuance that normal subagents compress away.
1 2d ago A 0 tokens
original MIT
Agent
When an agent hits a malformed state, its default is to pile on a tolerant parser, then a fallback, then a migration, then debug output. The correct fix is usually to enforce an invariant upstream so the bad state can never occur.
1 2d ago A 0 tokens
original MIT
Agent
For questions with second- and third-order consequences (a change → its implications → the blast radius of each implication), have layer-1 subagents each spawn layer-2 subagents, so every level of analysis runs in its own isolated context and only clean conclusions roll back up.
1 2d ago A 0 tokens
original MIT
Agent
When you want a coding agent to fix slow code, don't dump raw profiler output, give it a single tool that aggregates samples (frequencies, percentiles) into an analyzed view, because LLMs are bad at doing those computations themselves.
1 2d ago A 0 tokens
original MIT
Agent
Give teammates small, regularly-delivered tasks and include a devil's-advocate / security agent that critiques peers in real time.
1 2d ago A 0 tokens
original MIT
Agent
Split generation from verification across two agents: give the evaluator browser automation to click through the live app like a user and concrete runtime pass-thresholds, rather than letting the agent that wrote the code grade itself.
1 2d ago A 0 tokens
original MIT
Agent
When ending an agent-team session, send each teammate a 'save your work and confirm when ready' message and wait for the confirmation, rather than force-killing them mid-task.
1 2d ago A 0 tokens
original MIT
Agent
The TeamCreate/TeamDelete tools have been removed; with CLAUDECODEEXPERIMENTALAGENTTEAMS=1 every session has one implicit team and you spawn teammates simply by passing a name to the Agent tool.
1 2d ago A 0 tokens
original MIT
Agent
Subagents keep main context lean by handling research, log analysis, and exploration; they are poor at large edits due to compression loss.
1 2d ago A 0 tokens
original MIT