architect
01Agent
Use when Phase 3 design spec is needed before implementation begins.
3 2mo ago A 12 tokens
original MIT
3Stars on the repository
52Mods indexed here, across every type
2mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Agent
Use when API routes, service layer, or backend business logic is being changed.
3 2mo ago A 15 tokens
original MIT
brainstorm
03Agent
Use when 3 alternative approaches with trade-offs are needed before committing to one.
3 2mo ago A 15 tokens
original MIT
bug-analyst
04Agent
Use when a bug needs root-cause tracing from symptom to confirmed code location.
3 2mo ago A 15 tokens
original MIT
caveman
05Agent
Default output style for all aicrew skills and commands. Not opt-in.
3 2mo ago A 0 tokens
original MIT
cloud-expert
06Agent
Use when infra files (migrations, Dockerfile, deps, env config) changed.
3 2mo ago A 17 tokens
original MIT
Agent
Default: apply on every session. Not opt-in via /lean on.
3 2mo ago A 0 tokens
original MIT
Agent
Speculative-context scout: cheap graph-first discovery that emits a fixed SCOUT: schema for a capable main agent to verify and act on.
3 2mo ago A 28 tokens
original MIT
db-migration
09Agent
Use when database schema, model files, or migration files are being changed.
3 2mo ago A 14 tokens
original MIT
Agent
Use when frontend files (.tsx, .vue, components, routes) are being changed.
3 2mo ago A 17 tokens
original MIT
Agent
Four principles for disciplined, goal-driven coding — derived from forrestchang/andrej-karpathy-skills (MIT). Adapted and extended for the aicrew pipeline.
3 2mo ago A 0 tokens
original MIT
performance
12Agent
Use when performance is an acceptance criterion or a flow is measurably slower.
3 2mo ago A 15 tokens
original MIT
Agent
Use when a security review of changed files is needed.
3 2mo ago A 10 tokens
original MIT
Agent
Goal: survive usage timeouts and multi-tool parallel work by keeping durable, compact state files outside the chat.
3 2mo ago A 0 tokens
original MIT
Agent
Use when implementing code with strict RED→GREEN→REFACTOR enforcement.
3 2mo ago A 14 tokens
original MIT
terse
16Agent
Default: caveman/lean output style. See /Agents/agents/caveman.md.
3 2mo ago A 0 tokens
original MIT
Agent
Use in Phase 5 to audit test pyramid balance, coverage gaps, and test quality.
3 2mo ago A 17 tokens
original MIT