Browse the directory

Source-backed agent that reviews active Claude Code sessions and configuration for security gaps, cross-references the official security guidance, and produces a ranked remediation plan covering permissions, MCP trust, prompt injection, credential handling, and hook safety.

Source-backed agent that operates Claude Code inside GitLab CI pipelines — triaging pipeline failures, generating MR descriptions, running automated code review on diffs, and reporting findings back to merge requests via the GitLab API, using headless Claude Code with scoped tool permissions.

Source-backed Claude Code subagent prompt for reviewing Agent Skills before adoption or publication, checking SKILL.md scope, descriptions, invocation control, supporting files, tool permissions, helpfulness, safety, and privacy risks against official Claude Code skills guidance.

Source-backed agent that reviews and designs production Claude Agent SDK deployments, covering surface choice, tool and permission design, context and cost controls, session persistence, observability, and secure hosting, grounded in the official Agent SDK docs.

Source-backed agent that curates an organization's Agent Skills library, reviewing SKILL.md quality, descriptions and triggers, scope and precedence, tool restrictions, and invocation control so skills are discoverable and safe, grounded in the official Claude Code skills docs.

A reusable agent prompt for running a fleet of Claude Code background sessions from agent view (opened with the agents command). It triages which sessions need input, which are still working, and which have finished, then decides what to dispatch next, which to answer, and which to stop.

Source-backed agent for reviewing AI workflow submissions before publication with data-flow mapping, privacy metadata, governance evidence, MCP/tool authority checks, retention disclosure, and compliance escalation gates.

Source-backed agent for reviewing Atlas database schema migrations with migration lint, analyzers, drift detection, CI/CD evidence, dev-database simulation, rollout risk, rollback planning, and production safety gates.

Source-backed agent for reviewing typed Protobuf and gRPC API contract changes with Buf breaking-change evidence, lint results, buf.yaml policy, BSR schema checks, generated-code impact, consumer compatibility, and rollout decisions.

Source-backed agent for managing Changesets release cutovers, version PRs, changelog evidence, package bump decisions, pre-release mode, publish gates, and npm registry safety.

Source-backed agent that audits Claude Code auto mode configuration, reviewing the trusted environment list, allow, soft_deny, and hard_deny rules, the $defaults handling, and settings scope so the classifier blocks the right actions, grounded in the official auto mode docs.

Source-backed agent that plans and reviews an enterprise Claude Code rollout, covering server-managed settings, permission deny lists, managed MCP policy, fail-closed startup, hooks for audit, and what users cannot override, grounded in the official docs.

Source-backed agent that designs safe recurring Claude Code routines, turning a repeated task into a well-scoped, idempotent skill-driven workflow with clear triggers, permissions, and reporting, grounded in the official Claude Code skills docs.

Source-backed agent that coordinates parallel Claude Code sessions across git worktrees, planning isolation, base-branch choice, gitignored-file copying, subagent worktrees, and cleanup so parallel edits do not collide, grounded in the official Claude Code worktrees docs.

A reusable agent prompt that vets a Claude Code plugin or marketplace before a team installs it. It walks source trust, the plugin's Will-install list and bundled components (skills, agents, hooks, MCP servers, commands), the context-window cost, version pinning, and the user/project/local/managed install scope.

Source-backed agent for turning Codecov patch coverage, project coverage, flags, components, carryforward behavior, PR comments, and changed-file context into targeted regression test plans.

Source-backed agent for triaging dependency update pull requests with SemVer risk, Dependabot context, GitHub dependency review, OSV advisories, OpenSSF Scorecard signals, lockfile changes, test evidence, and privacy-safe notes.

Source-backed agent for cleaning up open-source GitHub issue queues with reproducibility checks, labels, issue types, milestones, assignees, project views, duplicate links, and maintainer-safe response drafts.

Source-backed agent for designing Inspect AI benchmark tasks, datasets, solver plans, scorer rubrics, model matrices, eval logs, and release-quality prompt evaluation decisions.

Source-backed agent for reviewing local-first Jupyter notebook workflows that use Jupytext text notebooks, paired notebooks, command-line sync, and version-control friendly reproducibility checks.

Source-backed agent for live production incident debugging with impact framing, timeline reconstruction, alert/log/trace evidence, rollback options, escalation boundaries, and privacy-safe incident notes.

Source-backed specialist agent for reviewing remote MCP authorization boundaries, protected resource metadata, resource indicators, token audience validation, token passthrough risk, and least-privilege scopes.

Source-backed agent that threat-models an MCP server before it is connected to Claude Code, covering trust verification, tool authority and side effects, prompt injection via tool output, network and credential exposure, and least-privilege mitigations, grounded in the official security docs.

Source-backed Claude Code subagent that reviews MCP tool result sizes against output token budgets, flagging tools that exceed the warning and default limits and recommending pagination, filtering, MAX_MCP_OUTPUT_TOKENS tuning, and per-tool size annotations.

Source-backed agent that reviews the container isolation posture of a NanoClaw deployment, checking filesystem mounts, per-agent scoping, credential vault routing, messaging channel permissions, and scheduled tasks before agents run with real access.

Source-backed agent for security review of open-source pull requests, including untrusted fork boundaries, GitHub Actions permissions, secret and code scanning, dependency review, provenance signals, and maintainer-owned merge recommendations.

Source-backed agent that reviews Claude Code plugins for dependency and compatibility issues, checking the plugin.json manifest, bundled components, external binaries like LSP servers, versioning, and namespace conflicts, grounded in the official Claude Code plugin docs.

Source-backed agent that reduces token cost and latency in Claude Code by improving prompt-cache hit rates, advising on stable context ordering, lean CLAUDE.md, on-demand skills, and MCP tool-search, grounded in the official docs.

Source-backed agent for reviewing rendered frontend changes with screenshots, visual comparison evidence, viewport layout checks, keyboard/focus paths, accessibility scans, CLS risk, and privacy-safe QA artifacts.

Source-backed agent that reviews Claude Code's sandboxed Bash configuration for safe boundaries, checking filesystem allow/deny paths, network allowlists, unsandboxed escape hatches, excluded commands, and credential read scope, grounded in the official Claude Code sandboxing docs.