Agent Claude Code
Backend engineer for entities, repositories, transactions, API contracts, schema design, and data integrity.
not rated 15 3mo ago A 23 tokens
original MIT
Agent Claude Code
Delivery manager that turns blockers, release tasks, rollback work, and maintenance actions into Beads-tracked delivery items.
not rated 15 3mo ago A 28 tokens
original MIT
Agent Claude Code
Delivery manager for backlog shaping, project planning, release readiness, rollback planning, and maintenance coordination.
not rated 15 3mo ago A 22 tokens
original MIT
Agent Claude Code
Pentest reviewer for scope control, recon planning, attack surfaces, OWASP checks, reproduction steps, and finding prioritization.
not rated 15 3mo ago A 30 tokens
original MIT
Agent Claude Code
QA automation engineer for unit, integration, API, UI, regression, fixtures, and automation maintainability.
not rated 15 3mo ago A 27 tokens
original MIT
Agent Claude Code
Quality reviewer for inspections, quality scoring, technical debt, code smells, maintainability, rework planning, and agentic fixture coverage.
not rated 15 3mo ago A 31 tokens
original MIT
Agent Claude Code
Requirements analyst that turns gaps, assumptions, constraints, and follow-up work into Beads-tracked items.
not rated 15 3mo ago A 28 tokens
original MIT
Agent Claude Code
Requirement specialist for vague asks, stakeholder context, constraints, acceptance criteria, and prioritized requirements.
not rated 15 3mo ago A 23 tokens
original MIT
Agent Claude Code
Research writer for literature review, repository ecosystem intake, screening, synthesis, gap analysis, evidence scoring, and formal written outputs.
not rated 15 3mo ago A 29 tokens
original MIT
Agent Claude Code
Security reviewer that turns findings, mitigations, and hardening work into Beads-tracked security items.
not rated 15 3mo ago A 27 tokens
original MIT
Agent Claude Code
Security reviewer for secure design, auth boundaries, secrets, misconfiguration, prompt injection, unsafe tool chains, and external skill provenance.
not rated 15 3mo ago A 30 tokens
original MIT
Agent Claude Code
Software architect that turns architectural risks, ADR follow-ups, and migration actions into Beads-tracked work items.
not rated 15 3mo ago A 28 tokens
original MIT
Agent Claude Code
Software architect for ADRs, decomposition, runtime and deployment views, quality attributes, tradeoff analysis, and integration design.
not rated 15 3mo ago A 28 tokens
original MIT
Agent Claude Code
System modeler that turns modelling inconsistencies, missing scenarios, and unresolved structural questions into Beads items.
not rated 15 3mo ago A 27 tokens
original MIT
Agent Claude Code
System modeler for use cases, domain models, sequence diagrams, activity flows, state models, and consistency checks.
not rated 15 3mo ago A 27 tokens
original MIT
Agent Claude Code
Test designer that turns missing coverage, weak oracles, and testability gaps into Beads-tracked work items.
not rated 15 3mo ago A 29 tokens
original MIT
Agent Claude Code
Test designer for partitions, boundaries, decision tables, state transitions, oracles, coverage strategy, and testability.
not rated 15 3mo ago A 27 tokens
original MIT
Agent Claude Code
UX researcher for personas, task analysis, usability studies, field work, and prototype critique.
not rated 15 3mo ago A 23 tokens
original MIT
web-engineer
19Agent Claude Code
Web engineer for routes, controllers, validation, sessions, browser-facing flow design, and design-to-code alignment.
not rated 15 3mo ago A 26 tokens
original MIT
Agent Claude Code
GitHub workflow engineer for issue-driven delivery, PR follow-through, CI failure triage, review readiness, host drift, and task-memory closeout.
not rated 15 3mo ago A 34 tokens
original MIT
Skill Claude CodeCodex
Review agent memory, handoff, retrieval, and learning designs for usefulness, provenance, privacy, staleness, and poisoning risk.
not rated 15 3mo ago A 33 tokens
original MIT
Skill Claude CodeCodex
Review agent run traces, eval summaries, tool logs, and handoff evidence before accepting a workflow result or self-improvement proposal.
not rated 15 3mo ago A 33 tokens
original MIT
Skill Claude CodeCodex
Shape ambiguous or frontier-agent work into a bounded agent task with outcome, scope, context, tools, autonomy level, and verification evidence.
not rated 15 3mo ago A 32 tokens
original MIT
Skill Claude CodeCodex
Review an agent workflow for where it may act autonomously, where it must ask, and where human approval is required.
not rated 15 3mo ago A 31 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: